© 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. 192952
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    copyright, dump, HTTPS, stream, prompt

    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
     DBMS
    0.52
    0.50
    口碑
    0.48
    ണേ
    0.47
     drept
    0.46
     імені
    0.46
    ash
    0.45
     
    0.45
     President
    0.44
     ireo
    0.44
    POSITIVE LOGITS
    ەل
    0.50
    Always
    0.49
     स्थिरता
    0.48
     बोझ
    0.47
     나의
    0.46
    Singleton
    0.46
    തോടെ
    0.46
    Curr
    0.45
    ఆర్
    0.45
    림픽
    0.45
    Activations Density 0.000%

    No Known Activations