© 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. 59326
    Prev
    Next
    INDEX
    Explanations

    posts describing content

    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
    .
    -2.50
    ↵↵
    -1.90
     but
    -1.87
    沨
    -1.81
    The
    -1.75
     we
    -1.73
     of
    -1.70
    "
    -1.62
     одной
    -1.59
    2
    -1.58
    POSITIVE LOGITS
    跸
    2.11
    现在的
    2.11
    鏐
    2.06
    鐃
    1.96
    ktionen
    1.91
    quelize
    1.78
    𖥧
    1.77
    榈
    1.77
    繍
    1.73
     ...
    1.72
    Activations Density 0.081%

    No Known Activations