© 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. 5984
    Prev
    Next
    INDEX
    Explanations

    money, score, snack, source

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

    This neuron strongly fires on unusually rare or domain‐specific tokens (e.g. proper names, uncommon words, or otherwise infrequent tokens).

    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
     리뷰
    0.84
    STRU
    0.79
     Novos
    0.77
    ᱶ
    0.75
    RESS
    0.74
     baseURL
    0.74
     vuccati
    0.72
    łości
    0.72
     truncate
    0.71
     Tanj
    0.71
    POSITIVE LOGITS
    atsioon
    0.77
     हिस्
    0.75
    -
    0.75
    ва
    0.75
     autre
    0.75
    д
    0.73
     сов
    0.71
    Aph
    0.71
    tmpobj
    0.71
    این
    0.71
    Activations Density 0.001%

    No Known Activations