© 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. 249893
    Prev
    Next
    INDEX
    Explanations

    seal off

    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
    堯
    0.47
    垚
    0.47
    ри
    0.47
     understands
    0.45
    妣
    0.44
     verstehen
    0.44
    린다
    0.43
    ü
    0.43
    理解
    0.43
    תר
    0.42
    POSITIVE LOGITS
     incons
    0.49
    Significant
    0.48
    0.48
     نہایت
    0.47
     மிகப்
    0.46
    lly
    0.45
    Autom
    0.45
    Usage
    0.44
    Union
    0.44
     одну
    0.44
    Activations Density 0.004%

    No Known Activations