© 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. 102895
    Prev
    Next
    INDEX
    Explanations

    enable macro commands

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

    instructions and processes

    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
     provisional
    0.44
    的主要
    0.44
    ది
    0.40
    tei
    0.39
    the
    0.39
     thei
    0.39
    ln
    0.39
     dimerization
    0.38
    topo
    0.38
     -
    0.38
    POSITIVE LOGITS
    क्षकों
    0.50
     Rush
    0.49
    ቶችን
    0.49
     Mark
    0.49
     Ро
    0.48
     Kraft
    0.47
    ہ
    0.46
     Simultaneously
    0.46
     Ру
    0.46
    ດ້ວຍ
    0.46
    Activations Density 0.002%

    No Known Activations