© 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. 192312
    Prev
    Next
    INDEX
    Explanations

    writing reviews and feedback

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

    outlier, learner, positivity, launches

    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
    ্দ্র
    0.55
    ard
    0.50
     Feelings
    0.50
    㞖
    0.50
     egym
    0.48
    ô
    0.47
    osz
    0.46
    々な
    0.45
    ız
    0.45
    
    0.45
    POSITIVE LOGITS
     rectangle
    0.47
     frosty
    0.45
     cloak
    0.45
     recursion
    0.45
    ประเภท
    0.45
     distracting
    0.44
    формация
    0.43
     where
    0.43
     that
    0.42
     massif
    0.42
    Activations Density 0.000%

    No Known Activations