© 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. 50898
    Prev
    Next
    INDEX
    Explanations

    that has

    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
     ст
    0.46
    ])[
    0.46
     ступен
    0.42
    arys
    0.42
     голов
    0.41
    Scaled
    0.41
     plunged
    0.41
     ОО
    0.41
    !",
    0.40
    !’
    0.40
    POSITIVE LOGITS
    guard
    0.45
    collections
    0.43
    eof
    0.41
     ँ
    0.41
    講
    0.41
    δέ
    0.41
    जरी
    0.39
     bahut
    0.39
    idän
    0.39
    ap
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.