© 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. 102862
    Prev
    Next
    INDEX
    Explanations

    .org

    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
    vgili
    -1.47
    簡單
    -1.45
     was
    -1.37
    ↵↵
    -1.30
    认真的
    -1.30
     terceira
    -1.27
     adage
    -1.26
     terlihat
    -1.25
    近く
    -1.23
    诙
    -1.21
    POSITIVE LOGITS
     this
    1.89
     that
    1.85
     -¿
    1.52
    ⃢
    1.49
     others
    1.41
     vā
    1.39
    Ꮴ
    1.38
     theſe
    1.38
     there
    1.38
    Ако
    1.37
    Activations Density 0.022%

    No Known Activations