© 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. 10089
    Prev
    Next
    INDEX
    Explanations

    Gh, Ah, H, h

    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
    ed
    4.16
    el
    3.60
    et
    3.31
    elje
    3.28
    e
    3.15
    en
    3.12
    عرف
    3.05
    elj
    3.01
    ة
    2.98
    ので
    2.87
    POSITIVE LOGITS
    s
    4.27
    ের
    4.01
    hh
    3.33
    ttps
    3.15
    hhh
    3.10
    ্‌
    3.01
    ్
    2.99
    ओं
    2.97
    ousands
    2.97
    sia
    2.95
    Activations Density 0.327%

    No Known Activations