© 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. 65803
    Prev
    Next
    INDEX
    Explanations

    India, polymers, punctuation

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

    physical harm, fragile bloom, cellulose material, lotus flower

    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
     enhances
    0.51
     assaults
    0.51
     Helps
    0.51
     Enhance
    0.50
    ミ
    0.49
    一本
    0.48
     enhancing
    0.48
    ਡ
    0.48
    エコ
    0.47
    モ
    0.47
    POSITIVE LOGITS
     સંબંધ
    0.53
     здесь
    0.50
     казино
    0.49
    <unused22>
    0.48
     sırasında
    0.48
     управля
    0.47
    
    0.46
     следующим
    0.46
    当前的
    0.46
     நுரையீரல்
    0.46
    Activations Density 0.002%

    No Known Activations