© 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. 120836
    Prev
    Next
    INDEX
    Explanations

    baby, owner, students

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

    concept art and poster designs

    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
    shapeColor
    0.56
    ㍍
    0.52
     व्यक्तिगत
    0.52
     intricately
    0.52
     προσωπ
    0.50
     ব্যক্তিগত
    0.49
     Еў
    0.49
    žite
    0.49
    lcii
    0.49
     kiş
    0.48
    POSITIVE LOGITS
    are
    0.50
     kompat
    0.48
     -
    0.47
     Board
    0.44
     Mountain
    0.43
    Mountain
    0.42
    unch
    0.42
    T
    0.41
    ере
    0.40
     functionality
    0.40
    Activations Density 0.001%

    No Known Activations