© 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. 7283
    Prev
    Next
    INDEX
    Explanations

    yahoo options /

    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
     এশিয়ার
    1.41
    getCharAt
    1.40
     टर्मिनल
    1.39
    迵
    1.36
     Các
    1.35
     ffilm
    1.34
    明
    1.33
    Кла
    1.31
    ٠
    1.31
    Все
    1.31
    POSITIVE LOGITS
    res
    1.30
    erten
    1.23
    posed
    1.18
     intended
    1.17
    mapsto
    1.17
    perin
    1.16
    longmapsto
    1.16
     fasten
    1.15
    ie
    1.14
    rej
    1.13
    Activations Density 0.003%

    No Known Activations