© 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. 21370
    Prev
    Next
    INDEX
    Explanations

    site and websites

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

    website construction and links

    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
    ري
    0.89
    تي
    0.89
    ر
    0.84
     Bedür
    0.81
    ﻰ
    0.80
    دين
    0.77
    ς
    0.77
     Ř
    0.76
    اي
    0.74
     بي
    0.74
    POSITIVE LOGITS
     i
    1.05
     sites
    1.01
     websites
    0.95
    or
    0.90
    ing
    0.90
     are
    0.89
     site
    0.88
     a
    0.86
     y
    0.85
     Site
    0.84
    Activations Density 0.087%

    No Known Activations