© 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. 29531
    Prev
    Next
    INDEX
    Explanations

    either or alternative

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

    either or choices

    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
    t
    1.11
    tia
    0.73
    ری
    0.70
    ু
    0.70
    tki
    0.70
    n
    0.69
    től
    0.68
    tio
    0.67
    lardan
    0.66
    تان
    0.64
    POSITIVE LOGITS
     either
    1.13
    要么
    1.02
     либо
    1.00
     veya
    0.98
    either
    0.97
     hoặc
    0.92
    もしくは
    0.82
     ឬ
    0.80
    либо
    0.78
     alebo
    0.77
    Activations Density 0.025%

    No Known Activations