© 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. 34-GEMMASCOPE-RES-131K
    7. 57096
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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_34/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
    เหรียญ
    -0.80
    当店
    -0.78
    Рус
    -0.76
     resisted
    -0.73
    вера
    -0.72
     screenWidth
    -0.72
    GetData
    -0.71
    ворю
    -0.70
    ッド
    -0.69
    国産
    -0.69
    POSITIVE LOGITS
    /#/
    0.85
     فهم
    0.83
    ără
    0.82
     albumin
    0.79
    setFlags
    0.78
     fortress
    0.78
    ็ก
    0.78
    }[!
    0.77
    ruti
    0.77
     ELL
    0.76
    Activations Density 0.001%

    No Known Activations