© 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. 107021
    Prev
    Next
    INDEX
    Explanations

    phrases like "throughout the" or "around the"

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

    browser, compare, or list

    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
     شرطونه
    0.54
    ۤ
    0.53
    ﾄ
    0.52
     آہ
    0.52
     گیر
    0.51
     بینی
    0.51
     법칙
    0.51
    Ⲗ
    0.51
    ﺡ
    0.51
     همچ
    0.50
    POSITIVE LOGITS
     peeling
    0.55
     grows
    0.53
     takeaways
    0.52
    im
    0.50
     milliliters
    0.50
    d
    0.50
     cities
    0.49
     closures
    0.49
     vegetables
    0.49
     containers
    0.49
    Activations Density 0.000%

    No Known Activations