© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12251
    Prev
    Next
    INDEX
    Explanations

    process and its operations

    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
    로
    3.64
    に
    3.16
    u
    2.97
    ა
    2.79
    ெற்ற
    2.75
    etro
    2.63
    ../
    2.61
     olmayan
    2.59
    quele
    2.57
    ḧ
    2.55
    POSITIVE LOGITS
    ের
    2.80
    icians
    2.73
    াবদ্ধ
    2.72
    ς
    2.62
    squared
    2.54
    nin
    2.52
    s
    2.50
    Ticks
    2.49
    intérêt
    2.44
     userRoutes
    2.44
    Activations Density 0.054%

    No Known Activations