© 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. 132143
    Prev
    Next
    INDEX
    Explanations

    research studies and reports

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

    exploring aims outlines assessment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    8
    0.53
    Pizza
    0.52
    6
    0.52
    7
    0.50
    Blockchain
    0.49
     ৮
    0.48
    营收
    0.47
    Automation
    0.46
     Pizza
    0.46
    C
    0.45
    POSITIVE LOGITS
     wannan
    0.54
     volition
    0.50
     ನನ್ನ
    0.48
     ನನಗೆ
    0.47
    特定の
    0.47
     tiges
    0.46
     fibrils
    0.46
     هنعمل
    0.46
     distinguishable
    0.45
     ನಾನು
    0.44
    Activations Density 0.007%

    No Known Activations