© 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. 62882
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes and categories

    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
    ようで
    -0.90
     bier
    -0.72
    شو
    -0.71
     Ники
    -0.70
     ícones
    -0.70
    iiii
    -0.69
    =&
    -0.69
     dobry
    -0.68
    enna
    -0.67
    gains
    -0.67
    POSITIVE LOGITS
     dopamine
    0.78
    .’’
    0.77
    ancial
    0.75
    忾
    0.75
     воро
    0.75
    enaire
    0.74
     ладо
    0.73
    rade
    0.72
    tosa
    0.71
    ιος
    0.71
    Activations Density 0.008%

    No Known Activations