© 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. 65031
    Prev
    Next
    INDEX
    Explanations

    contrasting ideas

    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
    .)-
    -1.54
     景色
    -1.48
    Ἡ
    -1.42
     chré
    -1.34
    ጴ
    -1.33
    pantaloni
    -1.31
     pioggia
    -1.28
     katholischen
    -1.27
    tênis
    -1.27
    ᅩ
    -1.27
    POSITIVE LOGITS
     we
    1.91
     [
    1.73
    :
    1.63
     I
    1.38
     our
    1.32
     product
    1.30
     /
    1.26
    靭
    1.23
     кроссовки
    1.21
    ;
    1.21
    Activations Density 0.013%

    No Known Activations