© 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. 10-GEMMASCOPE-RES-131K
    7. 85545
    Prev
    Next
    INDEX
    Explanations

    in no event shall

    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_10/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
     rése
    -2.80
    蟶
    -2.78
     benzin
    -2.55
    ޚ
    -2.52
     navide
    -2.33
     organisme
    -2.28
    髫
    -2.27
     verbe
    -2.23
     dokter
    -2.22
     râ
    -2.19
    POSITIVE LOGITS
     are
    3.42
     is
    3.42
     should
    3.16
     would
    3.11
    What
    2.86
     was
    2.77
     could
    2.75
    when
    2.69
    There
    2.64
    When
    2.58
    Activations Density 0.136%

    No Known Activations