© 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. 144673
    Prev
    Next
    INDEX
    Explanations

    classic tale, heroic role, look at

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

    descriptive qualities and states

    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
    /
    0.43
     predominantly
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
    。
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
     או
    0.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
    ↵↵↵↵↵↵↵
    0.34
     或
    0.34
     エ
    0.34
    POSITIVE LOGITS
     misfort
    0.37
     sufrimiento
    0.36
     convuls
    0.36
    ෙකු
    0.36
     ಸುದ್ದ
    0.36
     ప్రభుత్వ
    0.34
     görü
    0.34
     işlemler
    0.33
    કની
    0.33
    संबंध
    0.32
    Activations Density 0.024%

    No Known Activations