© 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. 34-GEMMASCOPE-RES-131K
    7. 64298
    Prev
    Next
    INDEX
    Explanations

    car, dress, appointment, or time

    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_34/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
    Conversely
    -1.20
     requisite
    -1.16
    🤮
    -1.15
    😡
    -1.13
     heretofore
    -1.13
    😤
    -1.09
     focussed
    -1.08
    🤬
    -1.08
    周囲
    -1.08
     commensurate
    -1.06
    POSITIVE LOGITS
     Hispanics
    1.27
     Hispanic
    1.23
     &&
    1.16
    好久
    1.13
    我看
    1.12
    ٫
    1.07
    ,&
    1.06
     they
    1.06
     남자
    1.06
    ヵ
    1.05
    Activations Density 0.054%

    No Known Activations