© 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-65K
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    function, systems, increases, chatbot

    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_65k_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
    觟
    1.37
    
    1.35
     キー
    1.34
    <0x16>
    1.31
     キャン
    1.28
     ティ
    1.28
     ネイビー
    1.27
     シェ
    1.23
     지방
    1.22
    놁
    1.22
    POSITIVE LOGITS
     thro
    0.81
     freak
    0.72
     fast
    0.71
     quick
    0.68
    quick
    0.65
     balloon
    0.64
    fast
    0.64
     beak
    0.62
    oo
    0.62
     n
    0.62
    Activations Density 0.000%

    No Known Activations