© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3105
    Prev
    Next
    INDEX
    Explanations

    programming related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Vectors
    0.38
    音樂
    0.36
    といえば
    0.35
    網站
    0.34
     আপ
    0.34
    arettes
    0.34
    %);
    0.33
    檔案
    0.33
    iostream
    0.33
    warna
    0.33
    POSITIVE LOGITS
     deserial
    0.51
     {@
    0.51
     serialized
    0.49
     instantiated
    0.46
     fluent
    0.43
     constructed
    0.42
     overridden
    0.42
     dieser
    0.42
     immutable
    0.42
     tormented
    0.42
    Activations Density 0.000%

    No Known Activations