© 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. 116807
    Prev
    Next
    INDEX
    Explanations

    multilingual citations and numbers

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

    SQL tables and analogies

    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
    秸
    0.50
    奇怪
    0.46
    经典
    0.46
    Slate
    0.45
    য়েছে
    0.44
    特定的
    0.43
     Chip
    0.43
     বিয়ে
    0.43
    ადა
    0.43
    强化
    0.42
    POSITIVE LOGITS
    ้า
    0.48
     ಎಷ್ಟು
    0.45
    WASHINGTON
    0.44
    ッティング
    0.44
     mencegah
    0.43
     書い
    0.43
     в
    0.42
     രണ്ട്
    0.42
    ート
    0.41
     유엔
    0.41
    Activations Density 0.000%

    No Known Activations