© 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. 59189
    Prev
    Next
    INDEX
    Explanations

    definitions

    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
    t
    -2.39
     ist
    -2.31
     are
    -2.27
     has
    -2.27
     [
    -2.19
     was
    -2.17
     WHEN
    -2.16
     FROM
    -2.14
     es
    -2.09
     das
    -2.08
    POSITIVE LOGITS
    skjaer
    2.34
    ांकि
    2.23
    狆
    2.08
     facilitar
    2.06
    uttgart
    2.05
     weken
    2.05
     związane
    1.98
    ार
    1.97
    绫
    1.95
     decoraciones
    1.92
    Activations Density 0.005%

    No Known Activations