© 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. 11733
    Prev
    Next
    INDEX
    Explanations

    mystery solving

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

    This neuron specializes in spotting numeric tokens (especially floating-point numbers or other multi-digit numeric identifiers).

    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
     معاملات
    0.82
    track
    0.81
    reduce
    0.80
    де
    0.79
    циям
    0.79
    G
    0.77
    T
    0.76
    curve
    0.75
    type
    0.74
    twist
    0.74
    POSITIVE LOGITS
    _%
    0.97
    _*
    0.79
     elicited
    0.78
     rDNA
    0.77
     attends
    0.77
     edizione
    0.76
    .(*
    0.76
    ,【
    0.76
     affirms
    0.76
    <%@
    0.75
    Activations Density 0.001%

    No Known Activations