© 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. 100745
    Prev
    Next
    INDEX
    Explanations

    providing examples or instances

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

    The neuron detects numeric expressions (especially decimal numbers) in the text.

    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
     Giugno
    -1.71
     Luglio
    -1.68
    袮
    -1.60
     Gennaio
    -1.57
    Эти
    -1.55
     Ottobre
    -1.49
     erfaring
    -1.48
    izoen
    -1.46
     mitä
    -1.42
     aktiviteter
    -1.41
    POSITIVE LOGITS
     such
    1.74
    )
    1.60
     statysty
    1.60
     present
    1.53
    ]
    1.48
     regarded
    1.41
    >
    1.36
     renowned
    1.32
    也想
    1.32
     compared
    1.23
    Activations Density 0.042%

    No Known Activations