© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151803
    Prev
    Next
    INDEX
    Explanations

    specialized roles or services

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

    patterns in lists

    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
     Wikip
    0.57
     Propaganda
    0.52
     Appropriations
    0.52
    idig
    0.52
    侩
    0.52
    
    0.52
    yatiti
    0.51
    estä
    0.50
     Technologie
    0.50
    szyst
    0.50
    POSITIVE LOGITS
    гут
    0.51
     recount
    0.49
    乗
    0.47
    <0x0D>
    0.47
     линии
    0.46
    мира
    0.46
     пря
    0.45
     a
    0.44
    淼
    0.44
     линия
    0.43
    Activations Density 0.001%

    No Known Activations