© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14047
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific entities

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

    The neuron fires on longer, relatively uncommon multi-syllable content words (e.g. “aliquam,” “molestie,” “flexitarian,” “quinoa,” “cold-pressed”).

    oai_token-act-pair · o4-miniTriggered 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
     propeller
    0.71
    ي
    0.71
    า
    0.67
     grinder
    0.66
     dipole
    0.66
    矽
    0.64
     idiot
    0.64
     skid
    0.64
    y
    0.63
    ////////////////
    0.63
    POSITIVE LOGITS
     незакон
    0.78
     leapt
    0.77
     knelt
    0.75
    lockSeconds
    0.73
    SpringMVCProject
    0.71
    রচনা
    0.70
    に加え
    0.70
    觊
    0.68
    যাত্রা
    0.67
     Broughton
    0.67
    Activations Density 0.018%

    No Known Activations