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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2010
    Prev
    Next
    INDEX
    Explanations

    as it appears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    흠
    1.34
     le
    1.30
     ver
    1.18
    细节
    1.14
     battle
    1.13
     appro
    1.12
     gele
    1.11
     kilometer
    1.11
     @
    1.10
     stolen
    1.07
    POSITIVE LOGITS
     مهر
    1.83
     কোন
    1.75
    ományos
    1.64
    ধিক
    1.60
    ोदर
    1.58
    ర్భ
    1.55
    
    1.54
    ோவின்
    1.54
    ጵ
    1.53
    嘧
    1.52
    Activations Density 0.000%

    No Known Activations