© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10408
    Prev
    Next
    INDEX
    Explanations

    vocabulary and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    йки
    3.43
     начать
    3.08
    가
    2.90
     orchestrated
    2.84
    resultados
    2.81
     нача
    2.72
    ક
    2.70
    තු
    2.69
     כן
    2.69
     congru
    2.68
    POSITIVE LOGITS
    ا
    3.86
    l
    3.56
    tól
    3.48
    س
    3.40
    лно
    3.38
    lı
    3.33
    t
    3.33
    ساس
    3.31
    ка
    3.19
    رة
    3.03
    Activations Density 0.071%

    No Known Activations