© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 193817
    Prev
    Next
    INDEX
    Explanations

    have faith

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

    usable information

    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
    tım
    0.49
    substituted
    0.46
    as
    0.45
    ரீ
    0.45
     leukemia
    0.44
     خیر
    0.43
    çao
    0.42
    
    0.42
    fru
    0.42
     ქვე
    0.42
    POSITIVE LOGITS
     viciss
    0.49
    してお
    0.46
     Symp
    0.46
     الوسط
    0.44
     Paints
    0.43
    勢
    0.43
     nata
    0.43
    すぐ
    0.42
     Hamb
    0.42
    健全
    0.42
    Activations Density 0.000%

    No Known Activations