© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13990
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
     of
    -1.38
     to
    -1.31
    There
    -1.30
     new
    -1.24
     Some
    -1.23
     create
    -1.23
     були
    -1.22
     as
    -1.17
     Sometimes
    -1.16
    return
    -1.14
    POSITIVE LOGITS
     ongles
    1.35
     lèvres
    1.20
     suministros
    1.19
     gants
    1.13
     symboles
    1.13
    uterte
    1.12
    ステム
    1.11
     exportación
    1.09
     arrêter
    1.09
     calles
    1.08
    Activations Density 0.000%

    No Known Activations