© 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. 255521
    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
    name
    0.48
    difference
    0.45
    direction
    0.45
    importance
    0.44
    spring
    0.44
    artificial
    0.44
    elevation
    0.44
    숟
    0.42
     وہ
    0.42
    categoryId
    0.42
    POSITIVE LOGITS
    డీపీ
    0.57
    DispatchRequest
    0.54
     nghị
    0.52
     lát
    0.51
     délé
    0.50
     í
    0.50
    szön
    0.50
     erz
    0.49
    гнозы
    0.49
    麸
    0.49
    Activations Density 0.000%

    No Known Activations