© 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. 14556
    Prev
    Next
    INDEX
    Explanations

    parsing code structures

    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
    ill
    1.07
     입니다
    1.06
    q
    1.05
    l
    1.00
    ra
    0.99
    liq
    0.97
    di
    0.89
    dan
    0.88
    ac
    0.87
    c
    0.87
    POSITIVE LOGITS
     quinquina
    1.65
     nessuna
    1.49
     discernible
    1.47
     qualunque
    1.45
    <unused1817>
    1.44
    <unused1012>
    1.44
     domesticated
    1.44
    <unused2009>
    1.43
     critérios
    1.43
    <unused1861>
    1.42
    Activations Density 0.010%

    No Known Activations