© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8107
    Prev
    Next
    INDEX
    Explanations

    thespruce.com URLs

    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
    <unused332>
    1.31
     violently
    1.30
    <unused946>
    1.28
    <unused134>
    1.27
    <unused1937>
    1.27
    <unused420>
    1.27
     vitesses
    1.26
     پیغم
    1.26
    <unused1932>
    1.26
    <unused1938>
    1.25
    POSITIVE LOGITS
     Ass
    0.90
     Su
    0.89
     TV
    0.85
     highlights
    0.83
     Ger
    0.82
     ASS
    0.81
     Tr
    0.81
     coordinator
    0.80
     timeline
    0.80
     Dall
    0.79
    Activations Density 0.034%

    No Known Activations