© 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. 38679
    Prev
    Next
    INDEX
    Explanations

    people in roles or positions

    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
    快点
    -1.39
     savag
    -1.26
     craz
    -1.23
     insanely
    -1.23
     gruesome
    -1.21
     revamped
    -1.21
     horrid
    -1.17
    V
    -1.17
     insane
    -1.17
    H
    -1.16
    POSITIVE LOGITS
     with
    1.40
     without
    1.27
     kurios
    1.24
     in
    1.23
     kartą
    1.18
     through
    1.14
    Zubereitung
    1.13
     llamaba
    1.11
     as
    1.09
     considerably
    1.09
    Activations Density 0.106%

    No Known Activations