© 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. 161801
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    words and phrases

    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
     tier
    0.53
     bifur
    0.51
     tiered
    0.48
     Tier
    0.46
    িকারী
    0.45
     ๆ
    0.44
     TIFF
    0.44
     பட்டிய
    0.44
     Birla
    0.44
     גבוה
    0.43
    POSITIVE LOGITS
    ح
    0.52
     музыку
    0.48
    لب
    0.47
    iculture
    0.46
    就这样
    0.46
     موسیقی
    0.44
     음악
    0.43
     paisaje
    0.43
    舖
    0.43
    تس
    0.42
    Activations Density 0.000%

    No Known Activations