© 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. 189308
    Prev
    Next
    INDEX
    Explanations

    places and services

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

    circular channel discharge

    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
    ای
    0.53
     física
    0.50
    ه
    0.46
     userData
    0.45
    Finder
    0.43
     বলছেন
    0.43
    userData
    0.43
     físicas
    0.42
    说
    0.42
     eléctricas
    0.42
    POSITIVE LOGITS
     Ansprüche
    0.48
     осуществляется
    0.46
     caes
    0.46
     vanligt
    0.46
     dauert
    0.45
     alltid
    0.45
     eneste
    0.45
    ϙ
    0.45
    ంలో
    0.45
    november
    0.45
    Activations Density 0.001%

    No Known Activations