© 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. 75750
    Prev
    Next
    INDEX
    Explanations

    physics and related study

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

    multi-lingual and specialized terms

    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
    b
    0.52
    n
    0.51
    ников
    0.50
    x
    0.50
    kins
    0.48
    start
    0.48
    nikov
    0.48
    採用
    0.47
     wire
    0.47
    y
    0.46
    POSITIVE LOGITS
    澍
    0.53
     ataques
    0.51
     Verständ
    0.50
     Huz
    0.49
    原始内容存档
    0.49
     poderos
    0.48
    လား
    0.48
     umiejęt
    0.47
    专属
    0.47
     সহজে
    0.47
    Activations Density 0.000%

    No Known Activations