© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 252399
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     disconcert
    0.47
     sited
    0.45
     Geography
    0.45
    uded
    0.45
    燚
    0.44
     хорошо
    0.44
     apprehended
    0.42
     notorious
    0.42
    akey
    0.42
     clever
    0.42
    POSITIVE LOGITS
    გნ
    0.56
    thren
    0.50
    ーブ
    0.47
     unwind
    0.47
    ವಿ
    0.46
     agarose
    0.45
    |+\
    0.45
     lắp
    0.45
    鐙
    0.45
    ♰
    0.44
    Activations Density 0.000%

    No Known Activations