© 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. 152724
    Prev
    Next
    INDEX
    Explanations

    bearings

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

    dedicated refined reporting

    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
    ጽ
    0.47
    ท
    0.46
    nn
    0.44
    ro
    0.44
    reject
    0.43
     Schreib
    0.43
    】
    0.43
     reven
    0.42
     Amaz
    0.42
    av
    0.41
    POSITIVE LOGITS
     bicovariant
    0.53
    转换为
    0.52
     nabí
    0.49
    Webhook
    0.48
     Україні
    0.48
    igrams
    0.47
    我相信
    0.46
     시간이
    0.46
     আইনশৃঙ্খলা
    0.46
    Ⴌ
    0.46
    Activations Density 0.001%

    No Known Activations