© 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. 22-GEMMASCOPE-2-RES-65K
    7. 1061
    Prev
    Next
    INDEX
    Explanations

    best practices

    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_65k_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
     oblast
    0.80
     Concern
    0.75
     prominence
    0.75
    statusCode
    0.74
     greats
    0.73
    ትን
    0.72
    successfully
    0.71
    要
    0.71
    seau
    0.71
    textBox
    0.71
    POSITIVE LOGITS
     suited
    2.15
    suited
    1.68
    owing
    1.58
    iality
    1.50
     geeignet
    1.49
     behaved
    1.45
    sellers
    1.38
    iary
    1.38
     practices
    1.29
     खासा
    1.29
    Activations Density 0.288%

    No Known Activations