© 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. 85220
    Prev
    Next
    INDEX
    Explanations

    certified DVD-ROM manufacturer

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

    computing and research fields

    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
     aldosterone
    0.46
    )=-
    0.46
     judicious
    0.46
     খাজ
    0.45
    veget
    0.45
     invertir
    0.45
     )-
    0.45
     restric
    0.44
     zmniejs
    0.44
     observaciones
    0.44
    POSITIVE LOGITS
    పై
    0.50
    牯
    0.49
    เห็น
    0.48
    뜻
    0.47
    考古
    0.46
    检
    0.46
     Thought
    0.45
     よう
    0.45
     Patienten
    0.44
    น้อง
    0.43
    Activations Density 0.000%

    No Known Activations