© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    I we statements

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

    I've, I'll statements

    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
     podían
    0.18
     powinien
    0.16
    。
    0.15
     när
    0.15
     เมื่อ
    0.15
     لینے
    0.15
     pouvaient
    0.15
     innymi
    0.15
     når
    0.14
    髀
    0.14
    POSITIVE LOGITS
     have
    0.18
     proudly
    0.18
     believe
    0.18
     are
    0.17
     got
    0.17
     intend
    0.17
    is
    0.16
     wholeheartedly
    0.16
    fe
    0.16
    re
    0.16
    Activations Density 0.808%

    No Known Activations