© 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. 192943
    Prev
    Next
    INDEX
    Explanations

    allowed, not allowed

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

    Query Likelihood Modeling

    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
    Negative Logits
     গাঙ্গ
    0.47
    UGG
    0.47
    NFT
    0.45
     …….
    0.45
     مشاهده
    0.43
     Jackpot
    0.43
     〈
    0.42
     Gabrielle
    0.42
    泻
    0.42
    TOTAL
    0.41
    POSITIVE LOGITS
     decorators
    0.52
    ને
    0.52
     нужны
    0.51
    ன்மைய
    0.48
    ements
    0.48
    攣
    0.48
    еты
    0.47
    𝘸
    0.47
     rollers
    0.47
     interfaces
    0.46
    Activations Density 0.002%

    No Known Activations