© 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. 16238
    Prev
    Next
    INDEX
    Explanations

    treated as independent

    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
    気
    1.06
    包括
    1.06
    主な
    0.99
    ബാ
    0.98
     incluem
    0.97
     continueRoutine
    0.94
     terlibat
    0.93
    ソ
    0.93
    Ker
    0.93
    லிக்க
    0.91
    POSITIVE LOGITS
     Junior
    1.04
    ugd
    0.95
    urai
    0.94
    izarro
    0.94
    uned
    0.94
    unov
    0.94
    urger
    0.93
    adito
    0.93
     wholes
    0.93
     เหมือน
    0.93
    Activations Density 0.000%

    No Known Activations