© 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. 139064
    Prev
    Next
    INDEX
    Explanations

    gallery west, foreign buyers, fabric case

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

    apt install

    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
     (
    0.52
     Care
    0.49
     vó
    0.48
    ewise
    0.47
     hears
    0.47
     глав
    0.46
     soms
    0.46
     many
    0.46
    禕
    0.46
    lar
    0.46
    POSITIVE LOGITS
    チケット
    0.43
     TERMIN
    0.43
    ენტი
    0.42
    ッサ
    0.42
     DISTRICT
    0.42
    セン
    0.41
    ңуз
    0.41
    couvrez
    0.40
    bahnhof
    0.40
     cowl
    0.39
    Activations Density 0.002%

    No Known Activations