© 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. 9329
    Prev
    Next
    INDEX
    Explanations

    standard phrases that introduce clauses

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

    Brain Fog

    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
    eração
    0.53
    PageIndex
    0.52
    eton
    0.47
    orel
    0.46
    dinger
    0.46
    ESIS
    0.45
    g
    0.45
     Nog
    0.44
    Vacuum
    0.44
    grave
    0.44
    POSITIVE LOGITS
     typedef
    0.50
    疼
    0.48
    宽
    0.48
    혔
    0.48
     rumen
    0.48
    出会
    0.47
     sillas
    0.47
     struts
    0.47
     transvers
    0.47
     vielf
    0.46
    Activations Density 0.000%

    No Known Activations