© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2147
    Prev
    Next
    INDEX
    Explanations

    focus and attention

    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
     surpluses
    2.67
     Nxf
    2.62
     vok
    2.46
    lying
    2.45
    ч
    2.40
    larda
    2.39
     Ensign
    2.36
     怪
    2.34
     tensile
    2.33
     fenders
    2.33
    POSITIVE LOGITS
    ூர
    2.69
    ચાર
    2.43
     бы
    2.39
     piedras
    2.37
    嗑
    2.35
    Lr
    2.35
    巢
    2.34
    itational
    2.33
    sortTable
    2.30
    raison
    2.28
    Activations Density 0.146%

    No Known Activations