© 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. 10829
    Prev
    Next
    INDEX
    Explanations

    asking if you have questions

    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
    ر
    3.12
    د
    3.07
    uert
    2.95
    ReferencePose
    2.94
    i
    2.88
    ി
    2.85
    rän
    2.80
    nements
    2.72
    scrollbar
    2.66
    sels
    2.61
    POSITIVE LOGITS
    णिज्य
    3.02
    丄
    2.95
    Sobre
    2.84
    ं
    2.84
    empire
    2.67
     paziente
    2.64
    Согласно
    2.63
    unary
    2.62
     rispar
    2.58
     digo
    2.57
    Activations Density 0.001%

    No Known Activations