© 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. 21751
    Prev
    Next
    INDEX
    Explanations

    numbers followed by parenthesis or dollar signs

    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
    雠
    -2.02
    䜣
    -1.95
    鼍
    -1.89
    耵
    -1.80
     they
    -1.79
    螃
    -1.75
    鐿
    -1.73
    蛲
    -1.72
    鹛
    -1.72
    珦
    -1.70
    POSITIVE LOGITS
     OGSÅ
    1.84
     of
    1.73
    。"
    1.72
    ！"
    1.68
    Shortly
    1.68
    Also
    1.58
    次回
    1.57
    autogui
    1.57
    不好
    1.56
     cheesy
    1.56
    Activations Density 0.007%

    No Known Activations