© 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. 223407
    Prev
    Next
    INDEX
    Explanations

    etc, usually, x/y/z

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

    dominating, Basic, herbs, museum, strategy

    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
     shove
    0.50
     ناح
    0.47
     उच्चतम
    0.47
     nodules
    0.46
     компонен
    0.46
    柿
    0.45
     мно
    0.45
    诲
    0.45
     pect
    0.44
    <unused40>
    0.44
    POSITIVE LOGITS
    τι
    0.47
    proving
    0.46
    won
    0.46
    chon
    0.46
    chakra
    0.46
    outez
    0.45
        
    0.45
    provided
    0.44
    irem
    0.44
    feit
    0.44
    Activations Density 0.000%

    No Known Activations