© 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. 11839
    Prev
    Next
    INDEX
    Explanations

    yourselftechOperators100

    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
    k
    2.99
    ر
    2.33
    й
    2.32
     inflict
    2.18
    ك
    2.18
     atual
    2.14
     enl
    2.09
    für
    2.09
    r
    2.07
    ה
    2.06
    POSITIVE LOGITS
     וכ
    2.60
    뭐
    2.57
    Pressed
    2.49
    哋
    2.44
    efficiencies
    2.18
    ølge
    2.10
    bbene
    2.10
     nostri
    2.09
    नंतर
    2.09
    ສຸດ
    2.06
    Activations Density 0.000%

    No Known Activations