© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8772
    Prev
    Next
    INDEX
    Explanations

    numbers and units like millimeters

    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
    i
    2.01
    ي
    1.97
    ل
    1.96
    я
    1.93
    ు
    1.70
    a
    1.69
    র
    1.68
    ל
    1.66
     indiquée
    1.58
    ть
    1.56
    POSITIVE LOGITS
     firstName
    1.82
     byteArray
    1.62
     shelled
    1.58
     semigroup
    1.57
     xAxis
    1.52
    firstName
    1.51
     deriv
    1.49
     особа
    1.48
    weds
    1.47
     дыха
    1.47
    Activations Density 0.136%

    No Known Activations