© 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. 10983
    Prev
    Next
    INDEX
    Explanations

    natively compiled applications

    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
    o
    1.87
    an
    1.86
    as
    1.72
    am
    1.54
    া
    1.51
    is
    1.50
    i
    1.44
    er
    1.39
    espace
    1.35
    y
    1.33
    POSITIVE LOGITS
     независимо
    1.58
    ->"
    1.56
    ⺝
    1.54
    так
    1.54
    单击
    1.54
    䥑
    1.51
    кает
    1.50
     bitOp
    1.50
    вля
    1.48
     trialComponents
    1.48
    Activations Density 0.000%

    No Known Activations