© 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. 10686
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and units

    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
     start
    1.17
    :
    1.13
     zuerst
    1.04
     vous
    1.00
     you
    0.99
    /
    0.98
     check
    0.98
    all
    0.97
    3
    0.96
    2
    0.95
    POSITIVE LOGITS
    ㎿
    1.72
     geopolitical
    1.57
    🛰
    1.53
    সংখ্যক
    1.50
     이상의
    1.44
     billions
    1.44
     astrophysical
    1.43
     Thousands
    1.42
     мили
    1.41
     সংখ্যক
    1.40
    Activations Density 0.359%

    No Known Activations