© 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. 188017
    Prev
    Next
    INDEX
    Explanations

    Pinkbook, movement, clutches, there, market, accept, PayPal

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

    instructed, prompt or task descriptions

    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
     ర
    0.56
     ده
    0.50
     पै
    0.49
    rän
    0.49
    uur
    0.48
     له
    0.47
    德
    0.47
     ऊंची
    0.46
     denen
    0.46
    ur
    0.45
    POSITIVE LOGITS
    ড্ড
    0.50
    ﺍ
    0.48
     poetry
    0.48
     Poetry
    0.47
    IContainer
    0.45
     eraser
    0.45
     Hamilton
    0.44
     sides
    0.43
     poesia
    0.43
     ensued
    0.43
    Activations Density 0.001%

    No Known Activations