© 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. 221094
    Prev
    Next
    INDEX
    Explanations

    from best choice products

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

    policy, lyrics, suggest, shadow

    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
     périph
    0.49
     zing
    0.48
     abges
    0.47
    ेज
    0.46
    ӳ
    0.45
     clés
    0.42
     দিয়েছেন
    0.41
     hacia
    0.41
    ing
    0.41
     ayer
    0.41
    POSITIVE LOGITS
    خرى
    0.52
    getNumberOf
    0.47
    ድረግ
    0.47
    。",
    0.46
    locatorType
    0.46
    חל
    0.45
    堝
    0.45
    larda
    0.44
    ליה
    0.44
    ání
    0.44
    Activations Density 0.001%

    No Known Activations