© 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. 152726
    Prev
    Next
    INDEX
    Explanations

    West district

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

    While, though, naturally, seems familiar

    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
    Not in Any Lists

    No Comments

    Negative Logits
     traumat
    0.42
    רוי
    0.42
    واي
    0.41
    ***
    0.41
    Corn
    0.41
     રમ
    0.41
     soon
    0.40
    粥
    0.40
     flick
    0.40
    рани
    0.40
    POSITIVE LOGITS
     หน้า
    0.54
    ্দি
    0.54
    ują
    0.52
     aident
    0.52
     urządzenia
    0.50
     लक्ष्यों
    0.50
     फेस
    0.49
    owane
    0.48
     ڕ
    0.48
     लक्ष्य
    0.47
    Activations Density 0.000%

    No Known Activations