© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183225
    Prev
    Next
    INDEX
    Explanations

    affected by

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

    physical processes and commands

    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
    Negative Logits
    无
    0.51
    本
    0.50
     。
    0.46
     circulate
    0.46
    ︽
    0.45
    Hình
    0.44
    Market
    0.44
    ிர
    0.43
    Publish
    0.43
    一
    0.42
    POSITIVE LOGITS
     स्क्रिप्ट
    0.46
     moored
    0.46
     kontek
    0.46
     ALLOYS
    0.45
     submar
    0.44
     pourront
    0.44
     erkannt
    0.43
     anek
    0.43
    𝚢
    0.43
     pourra
    0.42
    Activations Density 0.000%

    No Known Activations