© 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. 9276
    Prev
    Next
    INDEX
    Explanations

    data, json, html, xml formats

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

    extracting structured text information

    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
    膈
    0.49
     lutte
    0.49
     provoquer
    0.48
     helpen
    0.47
     помочь
    0.47
     luchar
    0.47
     свого
    0.46
    Tareas
    0.46
    餑
    0.46
     допомогти
    0.46
    POSITIVE LOGITS
     data
    0.68
    json
    0.67
     json
    0.62
    text
    0.61
     JSON
    0.59
    data
    0.58
     HTML
    0.57
     xml
    0.56
     XML
    0.56
     html
    0.55
    Activations Density 0.035%

    No Known Activations