© 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. 107589
    Prev
    Next
    INDEX
    Explanations

    want to

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

    pre words, size, trajectory, att

    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
    (
    0.47
     kiu
    0.45
     mules
    0.45
    LOT
    0.44
     otp
    0.44
     genitalia
    0.44
     trình
    0.44
     lobes
    0.43
    a
    0.43
     lyr
    0.42
    POSITIVE LOGITS
     पदाधिकारी
    0.53
     Readings
    0.51
     Informationen
    0.50
     Behör
    0.50
     Committee
    0.49
    ablemente
    0.48
     Blackboard
    0.47
     Feuerwehr
    0.47
     Wettbewer
    0.47
     जलाशय
    0.46
    Activations Density 0.000%

    No Known Activations