© 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. 4885
    Prev
    Next
    INDEX
    Explanations

    add to the

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

    The neuron is triggered by out‐of‐ordinary tokens such as proper names, acronyms, technical codes, or strings containing digits or uppercase letters.

    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
     foodservice
    0.71
     afar
    0.66
    🆚
    0.66
     moldings
    0.66
     brahman
    0.65
     accentuated
    0.65
     scones
    0.65
    muk
    0.64
     emojis
    0.64
     Etihad
    0.64
    POSITIVE LOGITS
     عجیب
    0.66
    ๊
    0.66
     अजीब
    0.65
     Weird
    0.62
    しかった
    0.62
     이걸
    0.61
    回収
    0.61
     뭔
    0.59
    weird
    0.59
     অবিশ্বাস্য
    0.57
    Activations Density 1.001%

    No Known Activations