© 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. 198845
    Prev
    Next
    INDEX
    Explanations

    fields of study and technical terms

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

    species motivations

    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
    Negative Logits
    㕷
    0.52
    ड्रीम
    0.50
    चलर्स
    0.46
    лили
    0.46
    PROXY
    0.46
    ことにより
    0.46
    उद्योग
    0.46
    чества
    0.45
    ीडियो
    0.45
    releases
    0.44
    POSITIVE LOGITS
     Macedonia
    0.50
    Ã
    0.48
    ্‌
    0.46
    TA
    0.46
     OVA
    0.46
     Azores
    0.46
     gloves
    0.45
     Gloves
    0.45
    pl
    0.44
     Rein
    0.44
    Activations Density 0.000%

    No Known Activations