© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69882
    Prev
    Next
    INDEX
    Explanations

    non-english characters and code fragments

    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
    糁
    -2.44
    Ꮉ
    -2.42
    摃
    -2.39
     sözler
    -2.39
     hadde
    -2.39
    ⢎
    -2.36
    糅
    -2.36
     стоковая
    -2.34
     مانت
    -2.34
    llavero
    -2.33
    POSITIVE LOGITS
    1
    3.75
    We
    3.33
    To
    2.92
     действия
    2.69
    As
    2.64
     The
    2.61
    \
    2.58
     
    2.55
    ”
    2.47
    いる
    2.42
    Activations Density 0.004%

    No Known Activations