© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130401
    Prev
    Next
    INDEX
    Explanations

    scheduling and tasks

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

    identities, circuit, watching

    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
    은
    0.54
    는
    0.52
     Tycho
    0.47
     बताए
    0.47
    ㅍ
    0.47
     ST
    0.47
    ↵
    0.46
    講師
    0.45
    を入れて
    0.45
     Chance
    0.45
    POSITIVE LOGITS
    人气
    0.55
     siya
    0.51
    篮球
    0.50
     hỗ
    0.47
     alluring
    0.46
    勛
    0.46
    आती
    0.46
    球员
    0.45
     saka
    0.45
    lés
    0.45
    Activations Density 0.000%

    No Known Activations