© 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. 6650
    Prev
    Next
    INDEX
    Explanations

    system requirements and functionality

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

    default system settings

    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
     newfound
    0.48
    成果
    0.44
    国内外
    0.44
    THERS
    0.41
     lahir
    0.41
     magari
    0.41
     நிச்சயம்
    0.40
    奮
    0.40
    熟悉的
    0.39
    予算
    0.39
    POSITIVE LOGITS
     proprietary
    0.68
     system
    0.67
     requires
    0.66
    系统
    0.64
     시스템
    0.63
     سیستم
    0.63
     require
    0.63
     configurable
    0.63
     Require
    0.63
    并没有
    0.61
    Activations Density 0.071%

    No Known Activations