© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163516
    Prev
    Next
    INDEX
    Explanations

    daily TV

    np_acts-logits-general · gemini-2.5-flash-lite

    Vegetable Glycerin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Divided
    0.56
     Algorithms
    0.50
     Gute
    0.47
    灵魂
    0.47
     Siddhartha
    0.47
    
    0.46
    先進
    0.45
    圍
    0.45
     розді
    0.44
    icill
    0.44
    POSITIVE LOGITS
    fromi
    0.49
    oz
    0.48
    ir
    0.47
    プ
    0.47
     inherit
    0.46
    ર
    0.46
    ร์
    0.46
     diversify
    0.44
     confection
    0.44
     liquidated
    0.44
    Activations Density 0.000%

    No Known Activations