© 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. 91018
    Prev
    Next
    INDEX
    Explanations

    assessment of value and importance

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

    following sequential terms

    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
    olées
    0.56
    an
    0.49
     黑
    0.49
    لے
    0.49
    r
    0.46
    اقة
    0.46
    দূত
    0.46
    n
    0.45
    ফোঁ
    0.45
     చేస్తుంది
    0.45
    POSITIVE LOGITS
     corrobor
    0.51
    РУ
    0.50
     gratifying
    0.47
     advantageous
    0.47
    有利
    0.47
     स्पष्ट
    0.46
     그러나
    0.46
    補充
    0.46
    重要な
    0.46
     predicament
    0.45
    Activations Density 0.001%

    No Known Activations