© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118942
    Prev
    Next
    INDEX
    Explanations

    Indian followed by Gujarat or Youth

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

    The neuron is triggered by numeric metadata in forum posts—counts, dates, and other numbers (e.g. post counts, join dates, related‐posts numbers).

    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
     ruine
    -1.46
     carrefour
    -1.45
     fjor
    -1.45
     Octobre
    -1.44
     nagu
    -1.44
     poë
    -1.39
    このように
    -1.37
     enfance
    -1.35
    よくある
    -1.34
    🕗
    -1.33
    POSITIVE LOGITS
     about
    2.03
     this
    1.61
     to
    1.52
    ᠁
    1.48
    am
    1.40
     gerekli
    1.40
     prácticamente
    1.35
    に戻る
    1.34
    跸
    1.34
     de
    1.34
    Activations Density 0.021%

    No Known Activations