© 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. 11107
    Prev
    Next
    INDEX
    Explanations

    network request headers

    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
    е
    2.94
     trapezium
    2.16
    ಗಾರ
    2.09
    о
    2.06
    િયા
    2.06
    и
    2.05
    а
    2.01
     сведения
    2.01
    ても
    1.99
     жить
    1.98
    POSITIVE LOGITS
    ्स
    2.71
    ları
    2.45
     ebbe
    2.40
    uance
    2.36
    ᴍ
    2.36
    هِ
    2.34
    なりません
    2.31
    sG
    2.28
    aac
    2.25
    س
    2.23
    Activations Density 0.008%

    No Known Activations