© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66271
    Prev
    Next
    INDEX
    Explanations

    adding information

    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_22/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
     favoris
    -1.54
     éta
    -1.38
     plafon
    -1.35
    gunas
    -1.31
     hés
    -1.30
    dann
    -1.30
     花纹
    -1.29
     レスト
    -1.29
    ♩
    -1.28
    鳚
    -1.28
    POSITIVE LOGITS
     also
    3.05
     "
    1.42
     również
    1.31
     in
    1.27
     likewise
    1.26
     también
    1.22
    ang
    1.20
     tiež
    1.20
    im
    1.16
    also
    1.16
    Activations Density 0.076%

    No Known Activations