© 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. 7037
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     вось
    1.78
    Ō
    1.78
    ﻄ
    1.72
    Deposito
    1.69
    Cemento
    1.66
    КО
    1.64
     भंडारण
    1.63
     Planta
    1.63
    اليا
    1.62
    \%).
    1.61
    POSITIVE LOGITS
    less
    1.23
    able
    1.23
    walla
    1.00
    r
    0.95
     support
    0.87
     external
    0.86
    house
    0.85
    ese
    0.84
    keeper
    0.83
     exchange
    0.82
    Activations Density 0.438%

    No Known Activations