© 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. 158650
    Prev
    Next
    INDEX
    Explanations

    governing persons

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

    complex concepts and systems

    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
    娇
    0.43
    Regardless
    0.43
    Sometimes
    0.43
     previamente
    0.43
    同样
    0.42
    Additional
    0.41
    di
    0.40
    }[
    0.40
    Horizontal
    0.40
    )~
    0.40
    POSITIVE LOGITS
     सर्वात
    0.54
     글로벌
    0.53
     करण्यासाठी
    0.49
     пайда
    0.49
     Fahrt
    0.49
    airline
    0.49
     leveraging
    0.48
    surfing
    0.48
     кух
    0.48
     মেয়র
    0.48
    Activations Density 0.002%

    No Known Activations