© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59259
    Prev
    Next
    INDEX
    Explanations

    Bhutan

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

    The neuron selectively activates on numeric tokens (including integers and decimals) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -2.72
    ：（
    -2.63
     impressively
    -2.44
     instantly
    -2.38
     blatantly
    -2.36
     antiquated
    -2.34
     streamlined
    -2.31
     from
    -2.31
     unequivocally
    -2.31
     nine
    -2.30
    POSITIVE LOGITS
     acclaimed
    2.86
    ⛛
    2.69
    瘣
    2.69
     AMAZING
    2.66
     MOST
    2.64
    ⚋
    2.63
     OTHER
    2.59
     immense
    2.59
     apporter
    2.58
     NEW
    2.56
    Activations Density 0.001%

    No Known Activations