© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71114
    Prev
    Next
    INDEX
    Explanations

    n followed by words starting with C, L, N, U

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    巿
    -3.59
     problemer
    -2.97
    AdvEx
    -2.92
     itſelf
    -2.81
     egent
    -2.78
     innumerable
    -2.73
    اً
    -2.70
    涠
    -2.67
    衞
    -2.66
     these
    -2.63
    POSITIVE LOGITS
     
    3.69
    If
    3.25
    In
    3.23
    0
    2.66
    ~~
    2.59
     وكان
    2.50
     وأ
    2.44
    possibly
    2.44
    ~~~~
    2.41
    苙
    2.41
    Activations Density 0.241%

    No Known Activations