© 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. 50831
    Prev
    Next
    INDEX
    Explanations

    sports and services

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

    common sense reasoning

    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
     extreme
    0.46
    ian
    0.45
    ↵↵
    0.44
     disruption
    0.44
    ให้กับ
    0.42
     vor
    0.42
     for
    0.42
    ier
    0.41
     critical
    0.41
     experience
    0.41
    POSITIVE LOGITS
    乒
    0.47
     Badminton
    0.46
     presença
    0.45
     теннис
    0.45
     chuột
    0.45
     badminton
    0.44
     Giappone
    0.44
     நன்கு
    0.43
     удовле
    0.43
    носить
    0.43
    Activations Density 0.000%

    No Known Activations