© 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. 10843
    Prev
    Next
    INDEX
    Explanations

    spring boot and plugins

    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
    اً
    2.10
    ا
    2.03
    i
    1.75
    s
    1.55
    ি
    1.50
     pozit
    1.46
    ly
    1.46
     unions
    1.42
     experimentally
    1.42
    =!
    1.41
    POSITIVE LOGITS
    ્ઞ
    1.71
    Aaj
    1.60
    ад
    1.57
    upaten
    1.50
     предлагают
    1.45
     Département
    1.45
    etime
    1.44
    Со
    1.43
    Ад
    1.43
    К
    1.41
    Activations Density 0.000%

    No Known Activations