© 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. 40828
    Prev
    Next
    INDEX
    Explanations

    Q: and Non-

    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
    0
    -2.50
    </em>
    -2.41
    渽
    -2.36
    媄
    -2.36
    ～、
    -2.36
    紲
    -2.28
     และ
    -2.25
    庒
    -2.22
    我喜欢
    -2.20
    我对
    -2.13
    POSITIVE LOGITS
     הא
    2.89
    e
    2.44
    '
    2.39
    {
    2.31
     inspirado
    2.30
     has
    2.27
    鍇
    2.20
    ا
    2.17
     atak
    2.17
     puramente
    2.17
    Activations Density 0.000%

    No Known Activations