© 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. 9860
    Prev
    Next
    INDEX
    Explanations

    Retrieval augmented generation

    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
    р
    2.09
    ie
    1.76
    it
    1.62
    p
    1.56
     importance
    1.42
    if
    1.41
    த்ரே
    1.37
    atonin
    1.31
    ম
    1.29
    ibility
    1.27
    POSITIVE LOGITS
    ه
    1.95
    هَا
    1.61
     previstas
    1.60
    o
    1.59
    ogonal
    1.59
    由於
    1.55
    cych
    1.52
    Notas
    1.41
    ර්ශ
    1.40
    要
    1.39
    Activations Density 0.000%

    No Known Activations