© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38689
    Prev
    Next
    INDEX
    Explanations

    profit and financial metrics

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

    The neuron fires on occurrences of “profit” (especially “net profit”) in financial‐report contexts, i.e. profit figures.

    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
    簠
    -2.73
    푔
    -2.52
    en
    -2.48
    𐀀
    -2.39
    疍
    -2.38
     –
    -2.38
    皤
    -2.34
    掼
    -2.33
     クリップ
    -2.31
    癭
    -2.31
    POSITIVE LOGITS
    .
    3.08
    蕩
    2.83
    While
    2.75
    Most
    2.70
     untuk
    2.69
    Although
    2.63
    It
    2.56
    Also
    2.52
    There
    2.48
    Even
    2.45
    Activations Density 0.003%

    No Known Activations