© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4292
    Prev
    Next
    INDEX
    Explanations

    world

    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_17_width_16k_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
    
    2.85
    ون
    2.53
    selves
    2.52
    ^{-}
    2.49
     logró
    2.40
    ylated
    2.33
    ormous
    2.33
    pageToken
    2.33
    번에
    2.32
    /-}$
    2.29
    POSITIVE LOGITS
    ளாவ
    3.50
    د
    3.28
    कर्मा
    3.19
    گیر
    2.90
     entier
    2.80
    ব্যাপী
    2.64
     przedstaw
    2.57
    वाइड
    2.55
    सनीय
    2.54
     textvariable
    2.45
    Activations Density 0.111%

    No Known Activations