© 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. 173906
    Prev
    Next
    INDEX
    Explanations

    personal data subject

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

    chart when, file when, flash directly

    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
    Negative Logits
     पत्ते
    0.54
    榛
    0.52
    फारिश
    0.49
    娠
    0.48
     अगली
    0.47
     روسی
    0.47
    REPEAT
    0.47
    RECOMM
    0.46
    笾
    0.46
    Noeud
    0.46
    POSITIVE LOGITS
    ↵↵
    0.62
     illusory
    0.54
     proves
    0.52
     rests
    0.52
    n
    0.52
     concess
    0.50
     dosen
    0.48
     or
    0.48
     concession
    0.48
    am
    0.48
    Activations Density 0.000%

    No Known Activations