© 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. 141387
    Prev
    Next
    INDEX
    Explanations

    constructive follow-up

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

    explaining why

    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
     (
    0.52
    憑
    0.49
     dataset
    0.47
    毫
    0.47
    JavaScript
    0.46
    dataset
    0.45
    基
    0.45
    ﹟
    0.44
     slate
    0.43
     基
    0.43
    POSITIVE LOGITS
     verurs
    0.61
     attrakt
    0.52
     बड़ा
    0.52
     dlou
    0.52
    伤害
    0.50
     elektri
    0.50
    说是
    0.50
     बड़ी
    0.49
     sekt
    0.48
     Henrik
    0.48
    Activations Density 0.000%

    No Known Activations