© 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. 44402
    Prev
    Next
    INDEX
    Explanations

    affirmations and interjections

    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
    0
    -1.85
    V
    -1.77
    )
    -1.77
     you
    -1.68
    C
    -1.63
    T
    -1.63
    /
    -1.61
    我把
    -1.60
    A
    -1.59
    --
    -1.57
    POSITIVE LOGITS
     also
    1.96
    軚
    1.63
    Also
    1.63
     sebagaimana
    1.54
    ignent
    1.53
     borse
    1.52
    ㄔ
    1.51
     Redacción
    1.48
    ！”
    1.46
    tiques
    1.45
    Activations Density 0.002%

    No Known Activations