© 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. 127425
    Prev
    Next
    INDEX
    Explanations

    place names and equipment

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

    CSV file processing

    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
    ल
    0.56
    ्रल
    0.51
    ाम
    0.49
    ف
    0.49
    ль
    0.48
    ЕР
    0.48
    л
    0.48
    ア
    0.47
     寝
    0.47
    сат
    0.47
    POSITIVE LOGITS
     ক্ষয়ক্ষতি
    0.46
    γον
    0.45
    scored
    0.45
    aterdag
    0.45
     ভিত্ত
    0.44
     zespo
    0.44
     offs
    0.43
     আনু
    0.43
     সুন
    0.42
    llan
    0.42
    Activations Density 0.001%

    No Known Activations