© 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. 205705
    Prev
    Next
    INDEX
    Explanations

    portions, hours, hectares, steps

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

    JSON format

    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
    ين
    0.52
    éticos
    0.51
     poucos
    0.51
    瀟
    0.50
     soluções
    0.50
    ブロック
    0.48
     ಇನ್ನೂ
    0.48
    ਾਵ
    0.48
     TRANSPORTURI
    0.48
    енера
    0.48
    POSITIVE LOGITS
    (
    0.61
     a
    0.53
    ()
    0.53
    Jaw
    0.51
    -
    0.51
     University
    0.49
    ’
    0.48
    ].
    0.47
     Jaw
    0.47
    Http
    0.46
    Activations Density 0.000%

    No Known Activations