© 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. 11510
    Prev
    Next
    INDEX
    Explanations

    Knock knock jokes

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

    This neuron strongly activates on numeric tokens—especially multi‐digit numbers and decimal figures (e.g. statistics, p-values, or measurements).

    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
    ladı
    0.97
     ntawm
    0.82
    ಶಿ
    0.79
     matières
    0.78
     threes
    0.78
    燴
    0.78
    ల
    0.77
     weist
    0.75
     thiab
    0.75
    giveness
    0.75
    POSITIVE LOGITS
    notation
    0.79
    cob
    0.75
    timestep
    0.75
     Quark
    0.75
    assumption
    0.75
    buffers
    0.74
    concent
    0.73
     Jdbc
    0.72
    ς
    0.72
    トラン
    0.71
    Activations Density 0.000%

    No Known Activations