© 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. 244552
    Prev
    Next
    INDEX
    Explanations

    discussing your project with client service

    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
     സി
    0.45
    ի
    0.45
    灯
    0.45
    łej
    0.44
     objection
    0.44
     nuovo
    0.44
     Stunde
    0.44
     új
    0.43
     unexplained
    0.43
     unbeaten
    0.43
    POSITIVE LOGITS
    watering
    0.43
     yay
    0.41
    Particular
    0.41
    DRO
    0.41
     creeps
    0.41
    撈
    0.40
     Penny
    0.40
    creep
    0.40
     croup
    0.40
    continental
    0.39
    Activations Density 0.001%

    No Known Activations