© 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. 113292
    Prev
    Next
    INDEX
    Explanations

    currency amounts and values

    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_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
    AutoModerator
    -1.55
     cucchiaio
    -1.39
    calça
    -1.39
    ској
    -1.22
    ciless
    -1.22
     Tüm
    -1.20
     入っ
    -1.20
    点此
    -1.18
    嘞
    -1.17
    十二月
    -1.16
    POSITIVE LOGITS
    pinephrine
    1.47
     officially
    1.32
    M
    1.30
    ซ์
    1.29
    cription
    1.27
    which
    1.27
     aren
    1.27
    ícias
    1.26
    2
    1.23
    liegenden
    1.23
    Activations Density 0.014%

    No Known Activations