© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    probabilities, combinations, and counting

    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
    ها
    1.92
    з
    1.81
    ן
    1.63
    त
    1.63
    er
    1.62
    െ
    1.61
    ма
    1.55
    ്‍
    1.46
    ر
    1.44
    ingly
    1.44
    POSITIVE LOGITS
    ະຍ
    2.00
    meler
    1.91
     timbers
    1.84
    ખ્ય
    1.82
    marine
    1.81
    לים
    1.74
    cz
    1.74
    iggs
    1.71
     GSi
    1.71
     Yesus
    1.70
    Activations Density 0.002%

    No Known Activations