© 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. 8528
    Prev
    Next
    INDEX
    Explanations

    following information disclaimers

    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
    🏽
    1.33
    Guj
    1.33
     मध
    1.30
    
    1.28
    🏼
    1.28
    ware
    1.26
    ニュー
    1.25
     professions
    1.25
    㫣
    1.24
    เหล
    1.24
    POSITIVE LOGITS
     Stelle
    1.33
    ੍ਹ
    1.31
     Terrasse
    1.20
     செய்தது
    1.20
     quyết
    1.18
    ficha
    1.18
     must
    1.18
     Must
    1.17
     ਇੱਕ
    1.15
    itr
    1.15
    Activations Density 0.164%

    No Known Activations