© 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. 12065
    Prev
    Next
    INDEX
    Explanations

    quoted code snippets

    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
    ش
    1.53
    ंख
    1.40
     प्यारी
    1.38
    èlement
    1.33
    Invoice
    1.31
    Totals
    1.28
     ন্য
    1.27
    xA
    1.26
    æng
    1.26
    ‬
    1.26
    POSITIVE LOGITS
     Gelegenheit
    1.83
     oportunidad
    1.82
     opportunity
    1.77
    nehmens
    1.67
    opportunity
    1.67
    機會
    1.66
    tedir
    1.66
     storytelling
    1.65
     truffle
    1.64
     oportunidades
    1.62
    Activations Density 0.121%

    No Known Activations