© 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. 67023
    Prev
    Next
    INDEX
    Explanations

    opening/closing component or grip

    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
    *
    -2.47
    (
    -2.28
    .
    -2.16
    {
    -2.03
    ...
    -1.92
    &
    -1.85
    2
    -1.73
    i
    -1.68
     красивая
    -1.66
    -1.66
    POSITIVE LOGITS
     karena
    2.23
    镚
    2.22
    鐧
    2.16
    )]

    1.98
    膂
    1.98
    metery
    1.98
    婼
    1.95
    荜
    1.94
    ?”
    1.93
    殲
    1.91
    Activations Density 0.016%
    No Known Activations