© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8733
    Prev
    Next
    INDEX
    Explanations

    toururu.com rabat.net

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

    role or persona prompts

    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_40_width_16k_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
     histological
    0.44
     aseptic
    0.40
     nutrient
    0.40
     outfield
    0.39
     agglut
    0.39
     aquifer
    0.39
    ⩽
    0.39
     elements
    0.38
     dyeing
    0.38
     cannons
    0.38
    POSITIVE LOGITS
    david
    0.67
    django
    0.57
    محمد
    0.56
    David
    0.55
    github
    0.54
     محمد
    0.53
    heroku
    0.52
    亚
    0.50
    google
    0.49
    Martin
    0.49
    Activations Density 0.010%

    No Known Activations