© 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. 60805
    Prev
    Next
    INDEX
    Explanations

    Edinburgh Fringe

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    提案
    0.55
     തല
    0.54
     ലി
    0.54
     Wikiseite
    0.54
     вікі
    0.54
     ナ
    0.53
     約
    0.52
     गूगल
    0.52
     Shankar
    0.51
     സാഹ
    0.50
    POSITIVE LOGITS
     allocations
    0.51
     injections
    0.50
     registrations
    0.47
    pmatrix
    0.45
     infections
    0.44
     Acts
    0.44
     peels
    0.44
    ↵
    0.44
     audits
    0.43
    relsen
    0.42
    Activations Density 0.000%

    No Known Activations