© 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. 127758
    Prev
    Next
    INDEX
    Explanations

    AUSTR ALIAN

    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
     '
    -2.41
     *
    -2.36
    '
    -2.28
    ’
    -2.27
    啖
    -2.22
    <bos>
    -2.19
    \
    -2.17
    縷
    -2.08
     enmar
    -2.05
    _{
    -1.97
    POSITIVE LOGITS
    ю
    2.64
     они
    2.44
     actualité
    2.34
    沵
    2.25
     They
    2.19
    ꦁ
    2.17
     ネタバレ
    2.09
    ية
    2.08
    特斯拉
    2.08
     ۳
    2.06
    Activations Density 0.002%

    No Known Activations