© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13199
    Prev
    Next
    INDEX
    Explanations

    support

    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_17_width_16k_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
    ع
    2.24
    ب
    2.10
    म
    1.96
    መሳሳይ
    1.88
    и
    1.87
    هم
    1.79
    س
    1.75
    ура
    1.73
     سبيل
    1.72
    у
    1.72
    POSITIVE LOGITS
    ्स
    1.98
    д
    1.98
    ן
    1.74
    tı
    1.67
     الفلسط
    1.61
    rt
    1.61
     wholeheartedly
    1.60
     AsRef
    1.57
    KeyUp
    1.56
    relatively
    1.56
    Activations Density 0.001%

    No Known Activations