© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    physics context, code comments

    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
     chaude
    -0.83
     répondre
    -0.79
    cuador
    -0.72
     linearized
    -0.71
     strlen
    -0.70
    ziele
    -0.70
    ゼン
    -0.69
    álna
    -0.68
     Wheaton
    -0.68
     الشمس
    -0.68
    POSITIVE LOGITS
     Flats
    0.79
    Vega
    0.69
     vanaf
    0.68
     flats
    0.66
     meson
    0.65
     Gegen
    0.65
     halide
    0.65
    ：[
    0.64
     messa
    0.64
    боро
    0.64
    Activations Density 0.029%

    No Known Activations