© 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. 102800
    Prev
    Next
    INDEX
    Explanations

    finished position or record

    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
     and
    -2.13
    cised
    -1.86
    âce
    -1.84
    饜
    -1.68
    ܖ
    -1.67
     maksimum
    -1.66
    tissimo
    -1.65
     siihen
    -1.64
     kedu
    -1.63
     چهارم
    -1.63
    POSITIVE LOGITS
     apolog
    1.84
    d
    1.78
    了两
    1.73
    (
    1.65
    -
    1.60
     actuelles
    1.59
    了很多
    1.52
    建議
    1.52
     ‘
    1.52
    Você
    1.49
    Activations Density 0.006%

    No Known Activations