© 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. 213292
    Prev
    Next
    INDEX
    Explanations

    tradition, preferences, ranges, springs, philosophical

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

    internal capacity and restrictions

    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
     及
    0.48
     bildir
    0.47
     പ്രവർത്തി
    0.46
     densely
    0.46
     crept
    0.45
     unlawfully
    0.45
     detected
    0.45
    pictureBox
    0.44
     hardly
    0.43
     detectable
    0.43
    POSITIVE LOGITS
    जी
    0.50
    ମ
    0.47
    شی
    0.47
    sacrifice
    0.46
    وی
    0.46
    ۲
    0.46
    మ్
    0.45
    ור
    0.45
    ल्
    0.45
    好み
    0.45
    Activations Density 0.000%

    No Known Activations