© 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. 34-GEMMASCOPE-RES-131K
    7. 99860
    Prev
    Next
    INDEX
    Explanations

    code identifiers followed by semicolon

    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_34/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
     there
    -1.95
     also
    -1.77
     for
    -1.57
     (
    -1.55
     on
    -1.43
     during
    -1.40
     [
    -1.34
     with
    -1.32
     or
    -1.31
     There
    -1.30
    POSITIVE LOGITS
     rapporter
    1.41
    ;
    1.31
     denna
    1.25
    Lesen
    1.24
    cestors
    1.24
    ᜀ
    1.23
    ;</
    1.23
     eaux
    1.23
    FOTO
    1.20
    ;
    1.20
    Activations Density 0.046%

    No Known Activations