© 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. 82629
    Prev
    Next
    INDEX
    Explanations

    Graphic Bookmark, enjoy financial, built-in

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

    explicit content and descriptions

    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
     rem
    0.49
     Powers
    0.46
     inept
    0.43
     incompetent
    0.42
    කින්
    0.41
    晔
    0.41
     eminent
    0.40
     recruit
    0.40
     remaining
    0.40
    ویه
    0.40
    POSITIVE LOGITS
    וס
    0.53
     של
    0.52
    /${
    0.50
    ตั้ง
    0.50
    ountain
    0.50
    aphthal
    0.47
     устро
    0.46
     ก็
    0.46
     новая
    0.46
     που
    0.46
    Activations Density 0.000%

    No Known Activations