© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11660
    Prev
    Next
    INDEX
    Explanations

    bills and hills

    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
    으로
    4.91
    ed
    3.16
    glm
    3.14
    ة
    3.02
    𝑡
    2.95
    चलिए
    2.91
    て
    2.78
    "\
    2.75
    ➸
    2.72
    ྱི་
    2.70
    POSITIVE LOGITS
    iteracy
    3.73
    ennium
    3.23
    িখিত
    3.16
    ুপ্ত
    3.08
    lllll
    3.04
    ੍ਹ
    3.02
    billy
    3.00
    llll
    2.85
    oughby
    2.83
    umination
    2.80
    Activations Density 0.204%

    No Known Activations