© 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. 58833
    Prev
    Next
    INDEX
    Explanations

    belongs to or includes

    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
    чені
    -1.54
     and
    -1.53
    __(
    -1.51
    uggets
    -1.48
    他的
    -1.48
    )*(
    -1.48
    🤸
    -1.48
    倨
    -1.45
    🌼
    -1.45
    менять
    -1.45
    POSITIVE LOGITS
     Vorteil
    1.68
    还有一
    1.63
     Aspekte
    1.49
     EVEN
    1.48
     the
    1.48
     are
    1.46
     tornou
    1.43
     начать
    1.43
    ➣
    1.41
     Then
    1.39
    Activations Density 0.012%

    No Known Activations