© 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. 128988
    Prev
    Next
    INDEX
    Explanations

    implements interfaces or classes

    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
    providedIn
    -1.22
     to
    -1.19
     episodio
    -1.10
     you
    -1.06
     phénomène
    -1.05
     abundances
    -1.05
    bandcamp
    -1.01
    breviations
    -0.98
    ям
    -0.97
     nuo
    -0.96
    POSITIVE LOGITS
    <bos>
    1.34
     ン
    1.12
    <0xA3>
    1.11
     bekämp
    1.11
    숀
    1.03
     umfasst
    1.02
    ggiata
    1.02
     exklu
    1.02
     parezca
    1.02
     répon
    0.97
    Activations Density 0.002%

    No Known Activations