© 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. 16-GEMMASCOPE-2-RES-262K
    7. 116371
    Prev
    Next
    INDEX
    Explanations

    religious inspiration and specific nouns

    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/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.64
     D
    0.51
    വ
    0.51
     V
    0.49
    വരെ
    0.48
    as
    0.47
      
    0.45
     memasuki
    0.45
    ยี
    0.45
    瀏
    0.44
    POSITIVE LOGITS
     оюндары
    0.59
     Outfitters
    0.52
     transmits
    0.50
    instag
    0.49
     eivät
    0.49
     derivations
    0.48
    ریٹر
    0.47
    ój
    0.47
    ！)
    0.47
    spannung
    0.46
    Activations Density 0.000%

    No Known Activations