© 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. 185258
    Prev
    Next
    INDEX
    Explanations

    hair, answered, needs, R, expected, back

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

    . True reclamation 1

    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
    o
    0.57
     Y
    0.53
    氏
    0.53
     CI
    0.50
     Eton
    0.50
    )
    0.50
     K
    0.48
     Z
    0.48
    CJK
    0.48
     Negro
    0.48
    POSITIVE LOGITS
    하거나
    0.49
     ना
    0.48
     તમારા
    0.46
     안전
    0.45
     혹은
    0.45
     прове
    0.45
    ௭
    0.44
     발생하는
    0.44
    ኪያ
    0.44
    བ
    0.43
    Activations Density 0.000%

    No Known Activations