© 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. 254720
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    विरुद्ध
    0.54
     definizione
    0.48
     entsprechenden
    0.48
     ਲ
    0.48
     অ্যান্টি
    0.46
     সম্পর্কিত
    0.46
     gegen
    0.45
     アップ
    0.45
     entsprechende
    0.45
     ایڈ
    0.44
    POSITIVE LOGITS
    castellan
    0.47
    Garden
    0.46
    看起来
    0.44
     cabinetry
    0.43
    사
    0.42
    يف
    0.41
    Nunca
    0.40
    会长
    0.40
    评
    0.40
    hei
    0.39
    Activations Density 0.001%

    No Known Activations