© 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. 180334
    Prev
    Next
    INDEX
    Explanations

    floor to ceiling windows

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

    mathematical summation formulas

    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
    Prayer
    0.43
    URL
    0.42
     revival
    0.42
    Streaming
    0.42
    부
    0.40
    Repeating
    0.40
     segítség
    0.38
    船
    0.38
    Some
    0.38
     surgery
    0.38
    POSITIVE LOGITS
     न्यायिक
    0.49
     bilgil
    0.48
    স্থানীয়
    0.46
     Cahill
    0.46
     znači
    0.45
     insightful
    0.44
     ingu
    0.44
     Golpe
    0.44
     ámbito
    0.44
    ुल्लाह
    0.44
    Activations Density 0.002%

    No Known Activations