© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 911
    Prev
    Next
    INDEX
    Explanations

    non-negative values and frequencies

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

    any real number

    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_53_width_65k_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
     yetiş
    0.57
    ᖕ
    0.53
     heartbreaking
    0.52
     personalidad
    0.52
     canoeing
    0.52
    鞏
    0.52
    ार्मिक
    0.52
     profesionales
    0.51
    讚
    0.51
     camaraderie
    0.51
    POSITIVE LOGITS
     nonnegative
    0.88
     nonzero
    0.82
     finitely
    0.77
     finite
    0.75
     linearly
    0.74
     countably
    0.74
     integer
    0.73
     pairwise
    0.73
     arbitrary
    0.71
     Euclidean
    0.71
    Activations Density 0.222%

    No Known Activations