© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4513
    Prev
    Next
    INDEX
    Explanations

    python code

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron identifies commercial product or device mentions—i.e. nouns naming items for sale or use in an e-commerce/advertising context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    spam or promotional content related to cell phone jammers and electronic devices.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    promotional e-commerce or catalog language about phone and surveillance-related gadgets, especially signal jammers, blockers, antennas, and GPS tracking devices.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     поку
    0.53
     banter
    0.50
     nause
    0.50
     hassles
    0.50
     tantrums
    0.48
     algum
    0.48
     heartwarming
    0.47
     rousing
    0.47
     stillness
    0.46
     nerd
    0.46
    POSITIVE LOGITS
    Acet
    0.53
    ốc
    0.49
    ūk
    0.49
    atility
    0.48
    Angular
    0.48
    Particle
    0.47
    Grupo
    0.47
    Vehicle
    0.47
    Cit
    0.47
    AGON
    0.47
    Activations Density 0.000%

    No Known Activations