© 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-16K
    7. 941
    Prev
    Next
    INDEX
    Explanations

    start at

    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_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
    ी
    3.14
    izzazione
    2.86
    een
    2.57
    Ş
    2.55
    ../../
    2.49
    tenance
    2.46
    re
    2.43
    izzare
    2.41
    tte
    2.41
    tedir
    2.39
    POSITIVE LOGITS
    at
    3.90
    ed
    3.71
    as
    3.51
    ITECTURE
    3.39
    ים
    3.32
    ের
    3.32
    力度
    3.30
    ة
    3.29
    ات
    3.29
     ^{\
    3.27
    Activations Density 0.381%

    No Known Activations