© 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. 123581
    Prev
    Next
    INDEX
    Explanations

    sponsored by

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

    but followed by can

    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
    Utt
    0.54
    種の
    0.51
    岡
    0.51
    лянчук
    0.50
    ardır
    0.49
    生ま
    0.48
    кут
    0.48
    定め
    0.47
    ਮ
    0.47
    ADES
    0.47
    POSITIVE LOGITS
     p
    0.55
    trace
    0.51
    param
    0.48
     has
    0.48
    vency
    0.47
    view
    0.46
    veno
    0.46
    ora
    0.46
    spice
    0.46
    rune
    0.46
    Activations Density 0.001%

    No Known Activations