© 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. 153993
    Prev
    Next
    INDEX
    Explanations

    Red Bull

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

    playing pretend on the computer

    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
     Winter
    0.48
     Latte
    0.48
     Wife
    0.46
     Care
    0.45
     UW
    0.45
     H
    0.43
     Paw
    0.42
     Wight
    0.42
     MW
    0.41
     Shipping
    0.41
    POSITIVE LOGITS
     obiettivo
    0.54
    நட
    0.50
     propriétaires
    0.49
    твер
    0.48
    ジェル
    0.48
     quadrados
    0.47
    ளைஞ
    0.47
    Т
    0.46
    Де
    0.46
     esterni
    0.46
    Activations Density 0.001%

    No Known Activations