© 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. 148810
    Prev
    Next
    INDEX
    Explanations

    `not` then `spread`, `tiger` then `it`, `pottery` then `at`, numbers then `.`, `. `not` then `spread`, `tiger` then `it`, `pottery` then `at`

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

    data formats and descriptions

    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
     descend
    0.55
    着
    0.55
     Verbind
    0.54
    ":["
    0.53
    的使用
    0.53
     marca
    0.52
    صل
    0.51
    斯特
    0.51
    疤
    0.51
     muž
    0.50
    POSITIVE LOGITS
    liye
    0.47
    ฬา
    0.47
    arj
    0.45
    lays
    0.44
    AlignCenter
    0.44
    falen
    0.44
     rebuke
    0.44
    AJ
    0.44
    productivity
    0.43
    ON
    0.43
    Activations Density 0.000%

    No Known Activations