© 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. 84978
    Prev
    Next
    INDEX
    Explanations

    name said, then after

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

    analyze critical chain

    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
    ب
    0.54
    ıları
    0.53
    aniline
    0.50
    秏
    0.49
    溽
    0.49
     volatiles
    0.49
    ərd
    0.49
    નગર
    0.48
     بازدید
    0.48
     نداشت
    0.48
    POSITIVE LOGITS
    いますが
    0.44
     mince
    0.42
    खी
    0.40
     створе
    0.40
     authorize
    0.40
     見
    0.39
     rozm
    0.38
     authorise
    0.38
     出
    0.38
     cause
    0.38
    Activations Density 0.000%

    No Known Activations