© 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. 29472
    Prev
    Next
    INDEX
    Explanations

    names with "George"

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

    perfect or perfectly

    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
     abnormally
    0.45
     síndrome
    0.44
     illnesses
    0.43
     INS
    0.43
     birthdays
    0.42
     suspensions
    0.42
     dplyr
    0.42
     ಧ
    0.42
     voltou
    0.41
     SAS
    0.40
    POSITIVE LOGITS
    Maxim
    0.57
    करने
    0.50
    argu
    0.49
    Haupt
    0.48
    Produ
    0.48
    畋
    0.48
    dört
    0.46
    the
    0.46
    Hlav
    0.46
    maxim
    0.45
    Activations Density 0.000%

    No Known Activations