© 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. 22-GEMMASCOPE-RES-131K
    7. 34316
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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_22/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
     any
    -1.24
    <bos>
    -1.23
     וכן
    -1.16
     國際
    -1.16
    中でも
    -1.16
     did
    -1.14
     those
    -1.12
    与此同时
    -1.09
    がなく
    -1.05
     could
    -1.04
    POSITIVE LOGITS
    ſelf
    1.38
    ſelves
    1.27
     contenta
    1.27
    ＄
    1.27
     ܠ
    1.23
    [
    1.23
    )=\
    1.23
    ociação
    1.21
    fatter
    1.20
    ّر
    1.20
    Activations Density 0.024%

    No Known Activations