© 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. 12792
    Prev
    Next
    INDEX
    Explanations

    pioneering and innovative companies

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

    innovation and specialized services

    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
    ພວກ
    0.52
    会让
    0.50
     तानाशाह
    0.50
    倞
    0.49
     आपत्ति
    0.49
     damal
    0.47
     κά
    0.46
    这类
    0.46
    霰
    0.46
     ಬಹಳ
    0.46
    POSITIVE LOGITS
     innovator
    0.54
     complemented
    0.52
     www
    0.50
     innov
    0.49
     pioneered
    0.49
    strateg
    0.49
     innovate
    0.48
    innov
    0.47
     uniquely
    0.46
     innovators
    0.46
    Activations Density 0.105%

    No Known Activations