© 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. 192354
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific nouns

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

    starting point / sequence qualifier

    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
    io
    0.61
     Y
    0.57
    ारा
    0.51
    ר
    0.48
    ो
    0.46
    toJson
    0.46
     (
    0.46
    ва
    0.46
    եռ
    0.46
    ித்த
    0.46
    POSITIVE LOGITS
     Consulate
    0.46
     Embroidery
    0.45
    錘
    0.45
     Printing
    0.44
     Nitrogen
    0.44
     abyss
    0.44
    㑒
    0.43
     लौटने
    0.43
    ควร
    0.43
    ধ্যার
    0.42
    Activations Density 0.000%

    No Known Activations