© 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. 258550
    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
     밝혔
    0.51
     interfaces
    0.50
    ności
    0.50
     combinations
    0.50
     Sauv
    0.49
     멀
    0.48
     สะ
    0.48
     niż
    0.48
     आफ्
    0.47
     निरंतर
    0.47
    POSITIVE LOGITS
    ín
    0.48
    directed
    0.45
    0.44
    ставля
    0.44
    по
    0.43
    ну
    0.43
    ignored
    0.43
    axiom
    0.43
    ome
    0.42
    accent
    0.42
    Activations Density 0.001%

    No Known Activations