© 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. 13-GEMMASCOPE-2-RES-16K
    7. 12451
    Prev
    Next
    INDEX
    Explanations

    int conversion

    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
     pò
    1.48
    rmann
    1.42
    netHex
    1.40
    ยน
    1.37
     tenei
    1.33
    xym
    1.28
    sembly
    1.28
    吅
    1.28
     decirle
    1.28
    gmzy
    1.27
    POSITIVE LOGITS
    пер
    1.17
    тори
    1.14
     উত্তরাধিকার
    1.12
     Objetivo
    1.09
     Residences
    1.09
     Wiel
    1.08
    правление
    1.06
     الأكثر
    1.06
    сле
    1.04
     Abschluss
    1.04
    Activations Density 0.000%

    No Known Activations