© 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. 103552
    Prev
    Next
    INDEX
    Explanations

    page numbers and lines

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

    line numbers and code context

    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
    ཥ
    0.36
    寯
    0.36
     الجزائر
    0.35
    зывают
    0.35
    钼
    0.35
    ченко
    0.35
    աստ
    0.34
     assuntos
    0.34
    レスレット
    0.33
     hoofd
    0.33
    POSITIVE LOGITS
    .
    0.42
     n
    0.39
     why
    0.38
     onward
    0.37
     onwards
    0.36
    og
    0.35
     phải
    0.35
     wish
    0.35
    ,
    0.35
     million
    0.34
    Activations Density 0.054%

    No Known Activations