© 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. 30237
    Prev
    Next
    INDEX
    Explanations

    There are

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

    Recorded History, stuffers, serializes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ৃত্বে
    0.53
    룻
    0.51
    ﻄ
    0.50
     danni
    0.48
    ﻌ
    0.46
    Zara
    0.46
    ্টি
    0.45
    ග්
    0.45
    ฏิ
    0.45
    waterslide
    0.45
    POSITIVE LOGITS
     (>
    0.50
     Сен
    0.45
     kriminal
    0.44
     nincs
    0.43
    另外
    0.43
    assium
    0.42
    ทาน
    0.42
     dimensions
    0.42
     encamin
    0.41
     ezért
    0.41
    Activations Density 0.000%

    No Known Activations