© 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. 10910
    Prev
    Next
    INDEX
    Explanations

    sleek, Sle

    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
    es
    -2.83
    ↵↵
    -2.78
    ꠥ
    -2.67
     {
    -2.66
    ”;
    -2.66
     sommige
    -2.52
    “
    -2.47
    嘁
    -2.45
    廡
    -2.42
    …”
    -2.39
    POSITIVE LOGITS
     konden
    2.61
     έχει
    2.53
    颀
    2.48
     occuper
    2.47
    栳
    2.41
    ｺ
    2.38
    ﾏ
    2.33
    貽
    2.31
    ｿ
    2.31
    also
    2.31
    Activations Density 0.002%

    No Known Activations