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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1842
    Prev
    Next
    INDEX
    Explanations

    subject to change or interpretation

    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_17_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
     смарт
    1.27
    "{!}
    1.23
     പക്ഷ
    1.20
    📌
    1.18
     குழந்தைகள்
    1.18
     gigante
    1.17
    𒋫
    1.15
    ফিন
    1.15
    kids
    1.14
    giants
    1.14
    POSITIVE LOGITS
     \
    1.48
    \
    1.42
     %\
    1.12
    %\
    1.09
    .\
    1.01
     :\
    1.01
     .\
    0.97
    <0xE3>
    0.92
     Sykes
    0.92
     Leslie
    0.87
    Activations Density 0.000%

    No Known Activations