© 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. 191313
    Prev
    Next
    INDEX
    Explanations

    spine wear

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

    all shots simultaneously

    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
    encil
    0.63
    o
    0.56
     Tours
    0.55
     Tour
    0.49
     Ventures
    0.49
     Grafton
    0.48
     Cheryl
    0.47
     Transportation
    0.47
     Brother
    0.47
     Tech
    0.47
    POSITIVE LOGITS
     athletes
    0.50
    ]<
    0.50
    ถ้า
    0.50
     nếu
    0.49
    相對
    0.49
     idxf
    0.47
    ｴ
    0.47
    Nếu
    0.47
    若
    0.47
    ანი
    0.46
    Activations Density 0.000%

    No Known Activations