© 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. 147408
    Prev
    Next
    INDEX
    Explanations

    announced by

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

    market dynamics, quality, data, culture

    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
    f
    0.64
    O
    0.54
    Christian
    0.49
     primaries
    0.48
    ↵↵
    0.48
    r
    0.47
    J
    0.46
    6
    0.45
    Argument
    0.44
    n
    0.44
    POSITIVE LOGITS
    ρων
    0.55
     Même
    0.54
    নির্ব
    0.52
     Rússia
    0.52
     İran
    0.50
     interação
    0.50
    ন্যায়
    0.50
     வண்ணப்பூச்சு
    0.49
     পর্যবে
    0.49
     região
    0.49
    Activations Density 0.000%

    No Known Activations