© 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. 13624
    Prev
    Next
    INDEX
    Explanations

    cheese and tofu

    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
    Baik
    -1.40
    咙
    -1.38
     amd
    -1.38
     Baik
    -1.36
     refugiados
    -1.34
    ve
    -1.31
     autres
    -1.26
     escuchado
    -1.26
     такой
    -1.24
     kollu
    -1.24
    POSITIVE LOGITS
     to
    1.60
     if
    1.55
     when
    1.52
    geſ
    1.42
    ynchronously
    1.39
    ensburg
    1.38
    在此
    1.36
    ghalaya
    1.33
    sizeCache
    1.32
     Investigaciones
    1.32
    Activations Density 0.015%

    No Known Activations