© 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. 12105
    Prev
    Next
    INDEX
    Explanations

    plunging into

    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
    el
    3.59
    am
    2.71
    in
    2.63
    zelfde
    2.48
    at
    2.46
    ن
    2.43
    l
    2.34
    ity
    2.33
    ס
    2.33
    нца
    2.33
    POSITIVE LOGITS
    я
    3.11
     lleno
    2.71
     aika
    2.43
    ᒻ
    2.37
     sane
    2.35
    ようになりました
    2.32
    txn
    2.30
    Список
    2.29
    ائل
    2.29
    つの
    2.26
    Activations Density 0.034%

    No Known Activations