© 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. 72704
    Prev
    Next
    INDEX
    Explanations

    in-person interviews

    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
    </h2>
    -1.76
    nteral
    -1.55
    laints
    -1.41
    Figure
    -1.38
    </em>
    -1.38
    atist
    -1.37
    tissa
    -1.37
    ↵↵↵↵↵↵↵↵↵↵↵↵
    -1.37
    vities
    -1.34
    ेत्र
    -1.34
    POSITIVE LOGITS
     because
    1.90
     our
    1.80
     when
    1.69
     with
    1.58
    我们会
    1.50
     we
    1.47
     for
    1.44
    我和
    1.42
     інших
    1.39
     other
    1.38
    Activations Density 0.175%

    No Known Activations