© 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. 121685
    Prev
    Next
    INDEX
    Explanations

    advisable to

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

    avocado and Respect

    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
    serrat
    0.48
    끝
    0.48
    Cycling
    0.48
     끝
    0.46
    陽
    0.45
    スト
    0.44
    ომ
    0.44
    äub
    0.44
    ぽ
    0.44
    듯이
    0.44
    POSITIVE LOGITS
     reporters
    0.48
     conveniently
    0.46
     beginners
    0.46
     कमाई
    0.45
     families
    0.45
     polled
    0.44
    л
    0.44
     commandments
    0.43
     outFile
    0.43
     contention
    0.43
    Activations Density 0.001%

    No Known Activations