© 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. 39445
    Prev
    Next
    INDEX
    Explanations

    only followed by qualifiers

    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
     these
    -1.56
     chicco
    -1.55
     lupo
    -1.52
     rito
    -1.45
     are
    -1.45
    퐼
    -1.43
     manqué
    -1.41
     camere
    -1.38
     albero
    -1.38
     venezia
    -1.38
    POSITIVE LOGITS
     "
    1.82
    </u>
    1.53
    显得
    1.48
    Appellee
    1.45
    وازم
    1.44
     Why
    1.41
    vaders
    1.34
    冱
    1.34
     pokud
    1.34
    quirer
    1.34
    Activations Density 0.037%

    No Known Activations