© 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. 10589
    Prev
    Next
    INDEX
    Explanations

    example inputs

    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
    -,
    1.14
    <unused2206>
    1.09
     extrema
    1.06
    ,[
    1.01
    <unused605>
    0.94
    <unused2157>
    0.93
    <unused589>
    0.93
    湮
    0.91
    ℝ
    0.91
    {},
    0.90
    POSITIVE LOGITS
    یت
    1.16
     ا
    1.06
     ين
    1.02
     های
    0.99
     פ
    0.97
     其他
    0.94
    ى
    0.94
     ¡
    0.93
     スタ
    0.90
     उपलब्ध
    0.88
    Activations Density 0.143%

    No Known Activations