© 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. 218436
    Prev
    Next
    INDEX
    Explanations

    Barn Bruno

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

    not positive or what is

    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
     Abnormal
    0.49
    orsky
    0.46
     निश्च
    0.46
     BECAUSE
    0.46
     because
    0.45
    æ
    0.45
     Hormone
    0.44
     Hours
    0.43
     hours
    0.43
     Overflow
    0.42
    POSITIVE LOGITS
     اسے
    0.48
    が生
    0.48
     хоть
    0.46
     temsil
    0.46
    اس
    0.45
     maupun
    0.44
    අ
    0.44
    겉
    0.43
     sempat
    0.43
     rappresenta
    0.42
    Activations Density 0.000%

    No Known Activations