© 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. 34-GEMMASCOPE-RES-131K
    7. 48656
    Prev
    Next
    INDEX
    Explanations

    expense and accounting terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ⒉
    -0.80
    振り返
    -0.80
    ゴリー
    -0.78
    Máy
    -0.77
    惬
    -0.76
    ckey
    -0.75
    financi
    -0.73
    遭到
    -0.73
    Matériel
    -0.73
     Cicero
    -0.73
    POSITIVE LOGITS
    MOH
    0.79
     Accum
    0.79
     expense
    0.79
     病
    0.76
     une
    0.75
     Accounts
    0.74
     Une
    0.73
    ongs
    0.70
     Acc
    0.69
     Advertising
    0.69
    Activations Density 0.006%

    No Known Activations