© 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. 15113
    Prev
    Next
    INDEX
    Explanations

    http/https URLs and components

    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
     encantador
    -1.29
     аллер
    -1.23
    恫
    -1.18
     favorecer
    -1.17
     on
    -1.16
    capai
    -1.16
     fotográfico
    -1.13
     proč
    -1.13
     some
    -1.09
     kanad
    -1.09
    POSITIVE LOGITS
    especially
    1.38
    actually
    1.30
     olie
    1.27
    镲
    1.25
    or
    1.23
     ребёнка
    1.21
    </b>
    1.20
    particularly
    1.19
     hela
    1.18
    </strong>
    1.17
    Activations Density 0.079%

    No Known Activations