© 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. 197198
    Prev
    Next
    INDEX
    Explanations

    non-latin characters

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

    efficiency matters

    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
     {
    0.61
     li
    0.61
     ARE
    0.58
     DOES
    0.55
     (
    0.55
     BUT
    0.54
     SET
    0.54
     WORK
    0.54
     RULE
    0.54
     x
    0.53
    POSITIVE LOGITS
    б
    0.48
    uların
    0.48
    św
    0.47
    கூ
    0.47
    ક
    0.47
    リム
    0.46
    ästä
    0.46
    стр
    0.46
    প্রা
    0.46
    ල
    0.45
    Activations Density 0.000%

    No Known Activations