© 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. 22-GEMMASCOPE-RES-131K
    7. 67547
    Prev
    Next
    INDEX
    Explanations

    FIG. 1

    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
    ,”
    -1.62
    眼前的
    -1.60
     sebagai
    -1.52
     uruguay
    -1.40
    ॅ
    -1.39
     viking
    -1.38
     GRATU
    -1.34
    ;");
    -1.34
    銕
    -1.33
    щё
    -1.31
    POSITIVE LOGITS
     divertidas
    1.31
     caption
    1.30
    atürk
    1.30
     anderen
    1.27
     únicas
    1.27
     miała
    1.20
     delicada
    1.19
     colorida
    1.18
     positivas
    1.16
     dziew
    1.15
    Activations Density 0.022%

    No Known Activations