© 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. 103063
    Prev
    Next
    INDEX
    Explanations

    avoid issues

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

    techniques or installation

    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
     Mustafa
    0.46
    ઃ
    0.46
     अभिगमन
    0.43
     ஜி
    0.42
    الحمد
    0.42
    uram
    0.42
     gacch
    0.42
    बेस
    0.41
    gür
    0.41
     მათი
    0.41
    POSITIVE LOGITS
    ↵↵
    0.44
    Snow
    0.43
    通话
    0.42
     nev
    0.42
     Irvine
    0.42
     নির
    0.41
    顽
    0.41
     terrible
    0.40
     nhiêu
    0.40
    现象
    0.40
    Activations Density 0.000%

    No Known Activations