© 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. 249957
    Prev
    Next
    INDEX
    Explanations

    color and texture

    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
    崽
    0.49
     Wellbeing
    0.46
     Others
    0.45
     Maple
    0.45
     which
    0.45
    酿
    0.44
    陆
    0.43
    牛仔
    0.43
     Shamrock
    0.43
    водит
    0.42
    POSITIVE LOGITS
    ﻜ
    0.48
     abitanti
    0.46
     ആക്രമ
    0.46
     villages
    0.45
    SourceName
    0.45
     ক্ষমতায়
    0.44
     mieszkań
    0.44
     alrededores
    0.44
     」,
    0.43
     asleep
    0.43
    Activations Density 0.000%

    No Known Activations