© 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. 10812
    Prev
    Next
    INDEX
    Explanations

    navigating app settings

    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
    adays
    2.59
    पणे
    2.58
    欖
    2.37
    आई
    2.37
    τα
    2.34
    צות
    2.34
    публи
    2.31
    Չ
    2.28
    је
    2.28
    кому
    2.28
    POSITIVE LOGITS
    s
    3.61
    いる
    3.48
    sellers
    3.48
    ের
    3.45
    берите
    3.33
    سلم
    3.07
    saint
    3.01
    shen
    3.00
    saldo
    2.98
    sam
    2.91
    Activations Density 0.010%

    No Known Activations