© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10403
    Prev
    Next
    INDEX
    Explanations

    ISO 9001:2015 token

    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
     dictated
    1.61
    disamb
    1.48
     Subsidi
    1.47
     shooting
    1.45
     tampil
    1.45
    >/</
    1.42
     depicting
    1.39
     verder
    1.39
    elijke
    1.37
     berapa
    1.37
    POSITIVE LOGITS
    ر
    1.83
    t
    1.79
    c
    1.70
    न
    1.54
    p
    1.51
    inode
    1.48
    age
    1.46
    rać
    1.45
    is
    1.44
    ния
    1.42
    Activations Density 0.002%

    No Known Activations