© 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. 72691
    Prev
    Next
    INDEX
    Explanations

    tags in code and data structures

    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
    AdvEx
    -3.30
    颏
    -3.13
    躂
    -3.05
    mmmm
    -2.94
    atação
    -2.91
    ୪
    -2.80
    阏
    -2.80
    鲧
    -2.78
    饪
    -2.73
    蚡
    -2.72
    POSITIVE LOGITS
    In
    3.42
    There
    3.31
    2
    3.23
    The
    3.02
    If
    2.97
     
    2.97
    --
    2.83
     impede
    2.81
    You
    2.78
    Although
    2.73
    Activations Density 0.007%

    No Known Activations