© 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. 22-GEMMASCOPE-RES-131K
    7. 128934
    Prev
    Next
    INDEX
    Explanations

    code and english text labels

    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_22/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
    かう
    -1.01
    💟
    -1.00
    ☘
    -1.00
    😪
    -0.99
    дати
    -0.98
     Fête
    -0.97
    ˮ
    -0.96
    😞
    -0.95
     triko
    -0.95
     américains
    -0.95
    POSITIVE LOGITS
    orghe
    1.07
     and
    1.02
     včetně
    0.90
     şeyi
    0.89
    tyfik
    0.88
     nejs
    0.87
    inheritDoc
    0.84
     encantó
    0.82
    」、
    0.82
    totalSupply
    0.81
    Activations Density 0.002%

    No Known Activations