© 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. 192337
    Prev
    Next
    INDEX
    Explanations

    necessary for Ariel

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

    concepts and tasks

    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
    -
    0.57
    _
    0.54
     kapat
    0.47
    ụ
    0.47
    额
    0.46
     Closure
    0.46
    ปิด
    0.44
    ă
    0.43
     Museum
    0.43
    దయ
    0.43
    POSITIVE LOGITS
     denaturation
    0.50
     irritated
    0.49
     עם
    0.48
     رسیده
    0.48
    condensation
    0.48
    னைய
    0.47
     विद
    0.46
    followed
    0.46
     vertes
    0.46
    sensitivity
    0.46
    Activations Density 0.000%

    No Known Activations