© 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. 192597
    Prev
    Next
    INDEX
    Explanations

    coverage, future, players, AM, will

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

    partner

    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
     دانشج
    0.48
    gadas
    0.47
     جیسے
    0.46
     ايضا
    0.46
     இந்தியாவின்
    0.45
    徠
    0.45
    颏
    0.45
     هوا
    0.44
     خی
    0.44
     επίσης
    0.44
    POSITIVE LOGITS
     There
    0.47
    ш
    0.46
    Recovery
    0.45
    Activity
    0.44
    Fan
    0.43
    recovery
    0.43
    TableCell
    0.42
    Org
    0.42
     recovery
    0.42
    തിയ
    0.41
    Activations Density 0.000%

    No Known Activations