© 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. 128514
    Prev
    Next
    INDEX
    Explanations

    attribute selectors

    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
     desmotiv
    -1.23
     and
    -1.12
     a
    -1.09
     rígido
    -1.09
     another
    -1.07
    %",
    -1.06
     
    -1.05
     Inseln
    -1.04
    ↵
    -1.02
     some
    -1.02
    POSITIVE LOGITS
    断了
    1.30
    ició
    1.21
    従来
    1.20
    PREPARATION
    1.16
    舩
    1.14
    Хотя
    1.13
    APPLAUSE
    1.11
    これまで
    1.11
    Даже
    1.10
    濵
    1.10
    Activations Density 0.003%

    No Known Activations