© 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. 22-GEMMASCOPE-2-RES-262K
    7. 11303
    Prev
    Next
    INDEX
    Explanations

    initial word fragments

    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_22_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
    tls
    0.87
    ที่สุด
    0.83
     das
    0.78
     numerous
    0.77
    encoded
    0.76
    h
    0.75
    不少
    0.75
    dto
    0.75
    tier
    0.73
    অধ
    0.73
    POSITIVE LOGITS
    funcionario
    1.01
    गिंग
    1.01
    ólito
    0.99
    czyny
    0.97
     すご
    0.96
    𝐺
    0.95
    kow
    0.95
    clesiast
    0.94
     necklaces
    0.92
    𝖆
    0.92
    Activations Density 0.002%

    No Known Activations