© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10603
    Prev
    Next
    INDEX
    Explanations

    hex color codes

    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_7_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
    camore
    1.77
    falcon
    1.77
     बदमाश
    1.73
    тын
    1.70
     ">
    1.70
     agosto
    1.67
     rectangle
    1.65
    bros
    1.65
    ceaux
    1.63
     +"
    1.63
    POSITIVE LOGITS
     pervasive
    1.57
     governmental
    1.52
     szükség
    1.51
     ganz
    1.48
    近平
    1.39
     nond
    1.38
     sự
    1.38
    บรร
    1.38
     Wissenschaft
    1.36
    บริ
    1.34
    Activations Density 0.057%

    No Known Activations