© 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. 91140
    Prev
    Next
    INDEX
    Explanations

    peace and rotary

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

    clarifying common misconceptions

    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
    哇
    0.53
    るので
    0.51
    ালোচনা
    0.49
     然後
    0.48
     所以
    0.48
     అభి
    0.48
     然后
    0.46
     টাকা
    0.46
    啦
    0.46
     ব্যাংক
    0.46
    POSITIVE LOGITS
     obliv
    0.56
     inseparable
    0.54
    ’,
    0.46
     Implicit
    0.46
     impatiently
    0.46
     haunting
    0.45
    implicit
    0.45
     blatantly
    0.45
     Shift
    0.44
     exasper
    0.44
    Activations Density 0.000%

    No Known Activations