© 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. 21144
    Prev
    Next
    INDEX
    Explanations

    angle of

    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
    袮
    -2.61
    ’
    -2.30
     书法
    -2.27
     Beſ
    -2.08
    狁
    -2.03
     leggero
    -2.03
     Obviously
    -1.94
    {
    -1.93
    結果は
    -1.90
    縂
    -1.90
    POSITIVE LOGITS
     of
    3.38
     '
    2.58
    </em>
    2.42
     \%
    2.41
     \&
    2.34
    汌
    2.27
     vores
    2.27
    晄
    2.23
    鰲
    2.23
    ſu
    2.20
    Activations Density 0.017%

    No Known Activations