© 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. 26626
    Prev
    Next
    INDEX
    Explanations

    where clauses

    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
    鲥
    -1.37
     plafon
    -1.34
     salari
    -1.32
     harap
    -1.32
     estadounid
    -1.27
    tió
    -1.24
     ciment
    -1.23
    เกง
    -1.23
     kulak
    -1.22
     rester
    -1.20
    POSITIVE LOGITS
     there
    1.63
     temos
    1.28
     například
    1.27
     ehemaligen
    1.26
    </sup>
    1.25
     specialized
    1.25
    ありません
    1.24
     such
    1.22
    gpr
    1.21
     permitiendo
    1.20
    Activations Density 0.018%

    No Known Activations