© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    Swipe Pages, necessary, Agency

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

    The neuron strongly activates on numeric tokens (especially decimal‐formatted numbers).

    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
    t
    0.95
    nummer
    0.74
    nutí
    0.73
    lagt
    0.73
    j
    0.72
     картины
    0.71
    lage
    0.70
    tter
    0.70
    ij
    0.70
    e
    0.70
    POSITIVE LOGITS
    ApiResponse
    0.75
     transceiver
    0.75
    ANIM
    0.75
    ACTIV
    0.74
     internalType
    0.74
     Unwrap
    0.73
    ギャ
    0.73
    였습니다
    0.73
    Expr
    0.71
    エコ
    0.71
    Activations Density 0.000%

    No Known Activations