© 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. 122864
    Prev
    Next
    INDEX
    Explanations

    information and facts

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

    institutional development in political science

    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
    ują
    0.49
    widgetTo
    0.48
    ayit
    0.48
     kitchenette
    0.48
    +#+#+
    0.47
    playerId
    0.46
    wertung
    0.46
    小物
    0.46
    вають
    0.46
     బొ
    0.46
    POSITIVE LOGITS
     appel
    0.54
     Fak
    0.48
     information
    0.48
     Informationen
    0.48
    '
    0.46
     Visible
    0.46
     ander
    0.45
     Ар
    0.45
     Facts
    0.45
     informations
    0.44
    Activations Density 0.001%

    No Known Activations