© 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. 21029
    Prev
    Next
    INDEX
    Explanations

    language code 'af'

    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
    啬
    -2.64
    寕
    -2.64
    䊉
    -2.61
    鹮
    -2.59
     แล้ว
    -2.42
    pecabe
    -2.39
    自身の
    -2.38
    ar
    -2.34
    拶
    -2.31
     από
    -2.28
    POSITIVE LOGITS
    I
    3.92
    --
    3.08
    af
    2.98
    ’
    2.83
    en
    2.81
    (
    2.56
    &
    2.55
    *
    2.52
    /
    2.39
    begin
    2.36
    Activations Density 0.007%

    No Known Activations