© 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. 111317
    Prev
    Next
    INDEX
    Explanations

    rushing yards

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on decimal-formatted numeric values (e.g., statistics like “62.75,” “15.5,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     cambio
    -1.62
    圌
    -1.47
     vieille
    -1.47
     sert
    -1.45
    雠
    -1.45
    鹇
    -1.45
     eterno
    -1.42
    </sup>
    -1.41
    ſſen
    -1.39
     realmente
    -1.39
    POSITIVE LOGITS
     singola
    1.59
    baikan
    1.49
    OrUpdate
    1.44
    Външни
    1.41
    ImagePath
    1.38
    ”？
    1.38
    AndPassword
    1.38
     with
    1.38
     essendo
    1.34
     possibilità
    1.34
    Activations Density 0.007%

    No Known Activations