© 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. 78187
    Prev
    Next
    INDEX
    Explanations

    online store or state of

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

    specific words followed by punctuation

    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
    し
    0.60
    たま
    0.55
    録
    0.55
    キラ
    0.54
    Italie
    0.54
    バン
    0.53
    binghamton
    0.52
    DESCRIPTOR
    0.52
    大切な
    0.52
    ご
    0.52
    POSITIVE LOGITS
     wen
    0.44
     w
    0.44
    cht
    0.44
    ковский
    0.42
     turnout
    0.40
     ~\
    0.40
     springfox
    0.40
    лады
    0.39
     atm
    0.39
     নাগ
    0.38
    Activations Density 0.001%

    No Known Activations