© 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. 50631
    Prev
    Next
    INDEX
    Explanations

    academic research and sourcing information

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

    online research and information gathering

    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
    笑容
    0.43
     невро
    0.42
    顛
    0.42
    उने
    0.42
     अभिनय
    0.41
     naše
    0.41
    員工
    0.40
    醜
    0.40
    nombre
    0.40
     bahagia
    0.39
    POSITIVE LOGITS
     Quellen
    0.72
     Sources
    0.72
     Bibliography
    0.71
     Research
    0.70
     Library
    0.70
     librarian
    0.70
     library
    0.69
     Librarian
    0.68
     research
    0.65
     sources
    0.64
    Activations Density 0.071%

    No Known Activations