© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44557
    Prev
    Next
    INDEX
    Explanations

    kanye west or code snippets

    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
    i
    -2.22
    1
    -1.88
    re
    -1.80
    琑
    -1.75
    at
    -1.75
    S
    -1.68
    m
    -1.64
    ar
    -1.62
    IS
    -1.61
    V
    -1.59
    POSITIVE LOGITS
    拶
    1.75
    銠
    1.69
    тения
    1.68
     to
    1.66
    得上
    1.64
     fueron
    1.52
    那里
    1.52
     erano
    1.51
     étaient
    1.47
    íodo
    1.45
    Activations Density 0.009%

    No Known Activations