© 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. 112842
    Prev
    Next
    INDEX
    Explanations

    Darkness auction, Overseas Payment, friend

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

    hydrating logging scripts

    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
     diffusing
    0.48
    acağız
    0.48
    кій
    0.47
    ギラ
    0.47
    フード
    0.47
    浣
    0.47
    informations
    0.46
    顽
    0.46
    )^{[\
    0.45
    蓬
    0.45
    POSITIVE LOGITS
     nausea
    0.49
     ভা
    0.45
     lo
    0.43
     versi
    0.42
     af
    0.42
     tras
    0.42
     Subset
    0.42
     Кра
    0.41
     khủng
    0.41
     e
    0.40
    Activations Density 0.000%

    No Known Activations