© 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. 186801
    Prev
    Next
    INDEX
    Explanations

    verbs related to cleaning and action

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

    lists, descriptions, or explanations

    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
    норий
    0.54
    ிருந்து
    0.52
    停车
    0.50
    冠军
    0.50
    КУ
    0.50
    玫
    0.49
    社会
    0.49
    코
    0.49
     거리
    0.49
     hạn
    0.48
    POSITIVE LOGITS
     animations
    0.48
     brunt
    0.47
     evaluations
    0.46
    tek
    0.46
    hael
    0.45
     mounds
    0.44
    haz
    0.43
     as
    0.43
     infusions
    0.42
     moulding
    0.42
    Activations Density 0.000%

    No Known Activations