© 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. 131874
    Prev
    Next
    INDEX
    Explanations

    selects or chooses

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

    electric, GKE, skyscanner

    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
    ༠
    0.56
     오늘
    0.54
     diferencial
    0.54
     rique
    0.52
     equid
    0.52
     certificados
    0.52
     이러한
    0.51
     certificado
    0.50
    ၆
    0.49
     elementos
    0.48
    POSITIVE LOGITS
    e
    0.60
    จาก
    0.52
    เย
    0.50
    engagement
    0.47
    ike
    0.45
     Hä
    0.45
    ೆಯಿಂದ
    0.44
    yout
    0.44
    ee
    0.43
     Ikea
    0.43
    Activations Density 0.000%

    No Known Activations