© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64976
    Prev
    Next
    INDEX
    Explanations

    kitchen equipment and utensils

    np_acts-logits-general · gemini-2.5-flash-lite

    command lines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    COME
    0.50
     गेहूं
    0.44
    께서
    0.43
    くなり
    0.43
     एजुकेशन
    0.40
    があり
    0.40
     anthracite
    0.40
    와
    0.40
    énés
    0.40
    باً
    0.39
    POSITIVE LOGITS
    as
    0.48
    las
    0.47
     MID
    0.47
    τας
    0.46
     solve
    0.46
    acı
    0.45
    ataa
    0.44
     .{
    0.44
    nes
    0.44
     CID
    0.44
    Activations Density 0.000%

    No Known Activations