© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21607
    Prev
    Next
    INDEX
    Explanations

    explicit prayer, prejudice, package, protocols, programming

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ႄ
    0.40
    acock
    0.38
     chuột
    0.38
    šť
    0.36
    ]);}
    0.36
    ihar
    0.36
    strup
    0.35
    oprop
    0.35
     otrzym
    0.35
    층
    0.34
    POSITIVE LOGITS
     पर्
    0.40
     Verein
    0.40
     велико
    0.38
     Ver
    0.38
     hinter
    0.38
     $=\
    0.38
     افس
    0.37
     cybers
    0.36
    ле
    0.36
    лим
    0.36
    Activations Density 0.000%

    No Known Activations