© 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. 21091
    Prev
    Next
    INDEX
    Explanations

    action negation

    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
    '
    -3.22
    Our
    -3.09
    Being
    -2.81
    One
    -2.77
    Unfortunately
    -2.73
    With
    -2.73
    This
    -2.70
    Only
    -2.64
    We
    -2.61
    Apparently
    -2.61
    POSITIVE LOGITS
    鸶
    2.58
    “
    2.56
    ;*/
    2.38
     he
    2.36
    ⩤
    2.34
    bluza
    2.25
     inauguración
    2.20
     we
    2.20
     zeigten
    2.20
     könne
    2.19
    Activations Density 0.013%

    No Known Activations