© 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. 34573
    Prev
    Next
    INDEX
    Explanations

    system property, variable, requirements

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

    system and technical applications

    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
    ين
    0.50
     comedic
    0.48
     die
    0.46
     spades
    0.46
     suscit
    0.46
     క
    0.46
    ية
    0.46
    லி
    0.46
    لي
    0.45
     পুনর্ব
    0.45
    POSITIVE LOGITS
    System
    1.45
    システム
    1.36
    SYSTEM
    1.35
     System
    1.34
     सिस्टम
    1.30
     SYSTEM
    1.28
    시스템
    1.25
     시스템
    1.24
     system
    1.23
    Sistema
    1.22
    Activations Density 0.034%

    No Known Activations