© 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. 254904
    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
     στην
    0.54
     উপস্থাপন
    0.54
    នៅលើ
    0.51
     特別
    0.50
    ũ
    0.50
     medicamentos
    0.49
    usión
    0.49
     போன்றவை
    0.48
     竹
    0.48
     构建
    0.47
    POSITIVE LOGITS
    o
    0.49
     flower
    0.46
     female
    0.46
     groups
    0.46
     unit
    0.45
    Been
    0.45
     European
    0.44
     Centennial
    0.44
     as
    0.43
    Unit
    0.43
    Activations Density 0.002%

    No Known Activations