© 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. 22-GEMMASCOPE-RES-131K
    7. 128680
    Prev
    Next
    INDEX
    Explanations

    error handling and responses

    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
    EXE
    -0.94
    grees
    -0.92
    Czech
    -0.88
    蛸
    -0.87
     cerveza
    -0.86
    ׇ
    -0.85
     nästan
    -0.85
    囯
    -0.85
     mudanças
    -0.84
    nachron
    -0.84
    POSITIVE LOGITS
    localctx
    1.13
    וּ
    1.10
    ündigen
    1.07
     العلاج
    1.02
    תודה
    1.01
     comunicare
    1.01
     вместо
    0.98
    udayaan
    0.96
    ciale
    0.94
    ־ה
    0.94
    Activations Density 0.016%

    No Known Activations