© 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. 14948
    Prev
    Next
    INDEX
    Explanations

    penguin or penguins

    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
    u
    -3.61
    鈰
    -2.89
    翃
    -2.72
    es
    -2.55
    ...?
    -2.53
    ta
    -2.48
    on
    -2.45
    ates
    -2.41
    “
    -2.39
    -2.38
    POSITIVE LOGITS
    because
    2.50
     pervasive
    2.38
     लिए
    2.34
    という感じ
    2.31
     teh
    2.30
    ྃ
    2.22
     hän
    2.20
    淠
    2.17
    grup
    2.16
    嗷
    2.16
    Activations Density 0.003%

    No Known Activations