© 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. 10312
    Prev
    Next
    INDEX
    Explanations

    refine, prototype, Pulmonary Syndrome, Token, Compress, connection

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

    The neuron primarily detects numeric tokens representing decimal values (e.g. DOIs, ISSNs, or other floating-point 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
    м
    1.02
    يند
    0.95
     seta
    0.88
    وني
    0.82
    ब्र
    0.81
    يني
    0.81
     armes
    0.76
    બ
    0.76
    ا
    0.76
    ｏ
    0.75
    POSITIVE LOGITS
     restricciones
    0.77
    iro
    0.73
    Serialized
    0.69
     pequeños
    0.68
    lonitrile
    0.68
    售后
    0.67
     cinética
    0.67
     lòng
    0.66
     añad
    0.66
    CIÓN
    0.66
    Activations Density 0.000%

    No Known Activations