© 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. 254411
    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
     alebo
    0.52
     immunos
    0.45
     nebo
    0.45
     Immun
    0.44
     -
    0.44
     ${
    0.44
     Rh
    0.44
     eller
    0.44
     {
    0.44
     )
    0.44
    POSITIVE LOGITS
    РА
    0.55
    ДЕ
    0.54
     лай
    0.53
    চূ
    0.52
    чер
    0.52
    тер
    0.51
    б
    0.51
    ЛЬ
    0.50
    ска
    0.50
    зад
    0.49
    Activations Density 0.001%

    No Known Activations