© 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. 11249
    Prev
    Next
    INDEX
    Explanations

    if statements

    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
    ar
    3.46
    ন
    2.85
    ع
    2.76
    र
    2.71
    न
    2.70
    ँच
    2.52
    ن
    2.49
    arasi
    2.49
    нской
    2.43
    nel
    2.35
    POSITIVE LOGITS
    MainBinding
    3.17
    𝘴
    2.64
    𝘣
    2.54
    동안
    2.51
    స్
    2.47
    𝘩
    2.45
    Shir
    2.41
    <footer>
    2.36
    亻
    2.35
    폈
    2.34
    Activations Density 0.206%

    No Known Activations