© 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. 146709
    Prev
    Next
    INDEX
    Explanations

    nonstick cookware , Chrysler , lock screen , surviving so

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

    describing impressions or qualities

    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
    스와
    0.52
    es
    0.51
    ו
    0.49
    зво
    0.48
     тұ
    0.45
    령
    0.44
    שׁ
    0.43
    ான
    0.42
    וו
    0.42
    ಸ್‌
    0.42
    POSITIVE LOGITS
    ieli
    0.50
     حبايبي
    0.49
    UMO
    0.49
    áme
    0.49
     अपना
    0.46
     vroeg
    0.46
     ECC
    0.46
    হ্যা
    0.46
    ilia
    0.45
     ECM
    0.45
    Activations Density 0.000%

    No Known Activations