© 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. 117970
    Prev
    Next
    INDEX
    Explanations

    works and their features

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

    works and impact

    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
    这
    0.41
     इसे
    0.40
    Giovanni
    0.39
    atin
    0.39
    Episode
    0.38
    Созда
    0.38
     חד
    0.38
    (
    0.38
    𝙊
    0.38
    iniz
    0.38
    POSITIVE LOGITS
     लोकप्रिय
    0.50
     renowned
    0.49
    特色
    0.49
     होतात
    0.49
     renown
    0.48
     AGR
    0.47
     famed
    0.47
     unrival
    0.46
     പ്രസി
    0.46
    の特徴
    0.46
    Activations Density 0.205%

    No Known Activations