© 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. 81723
    Prev
    Next
    INDEX
    Explanations

    gas alarm loudly

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

    renewal applications and treatment courses

    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
     laughs
    0.48
     warmth
    0.47
     sleepy
    0.46
    朗
    0.46
    特に
    0.45
    憲
    0.44
     compliments
    0.44
     cold
    0.44
    じて
    0.43
    เย็น
    0.43
    POSITIVE LOGITS
    Università
    0.53
     నిర్వహ
    0.49
     الرئيسي
    0.48
     હો
    0.47
    ÃO
    0.47
     Université
    0.47
     ສ
    0.47
    Université
    0.47
     사용하여
    0.46
     ఎక్కువ
    0.44
    Activations Density 0.002%

    No Known Activations