© 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. 129350
    Prev
    Next
    INDEX
    Explanations

    Award of the Year

    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
     セット
    -1.08
    Set
    -1.06
    m
    -1.04
    Is
    -1.00
    I
    -1.00
    b
    -0.99
    More
    -0.99
    But
    -0.97
    Call
    -0.96
    G
    -0.96
    POSITIVE LOGITS
    鮠
    1.24
     podľa
    1.20
    してほしい
    1.17
    膂
    1.16
    Inoltre
    1.11
    ブログ村
    1.11
     podrob
    1.11
     esteve
    1.10
    Ferdin
    1.09
     국가
    1.09
    Activations Density 0.030%

    No Known Activations