© 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. 235740
    Prev
    Next
    INDEX
    Explanations

    opinion paragraphs

    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
     권
    0.52
     관련된
    0.52
    旛
    0.52
    泹
    0.52
     صلی
    0.52
     সৌর
    0.52
     પોતા
    0.51
     різ
    0.50
     Балтбет
    0.50
    ầng
    0.49
    POSITIVE LOGITS
    ,
    0.70
    -
    0.62
     industri
    0.58
    in
    0.57
    an
    0.57
    B
    0.56
    W
    0.55
    T
    0.55
    0.55
    er
    0.54
    Activations Density 0.000%

    No Known Activations