© 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. 22418
    Prev
    Next
    INDEX
    Explanations

    quotation marks and special characters

    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
    ↵↵
    -1.99
     (
    -1.86
    ).
    -1.72
     &
    -1.72
    \
    -1.68
     –
    -1.66
     —
    -1.59
     a
    -1.58
    ze
    -1.48
    on
    -1.47
    POSITIVE LOGITS
     bambu
    1.94
     短发
    1.80
    引言
    1.78
     パッド
    1.78
     收納
    1.77
     Buat
    1.73
     utop
    1.73
     Bikin
    1.71
     Jika
    1.69
     brilla
    1.69
    Activations Density 0.004%

    No Known Activations