© 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. 68018
    Prev
    Next
    INDEX
    Explanations

    structured data, media

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

    The neuron fires on numeric literals (especially integers and decimals) 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
     incroy
    -1.59
    Bahkan
    -1.59
    Manfaat
    -1.58
     récents
    -1.55
     parfü
    -1.53
     armée
    -1.53
     rumores
    -1.52
    Meskipun
    -1.52
     vulgaires
    -1.52
    Seperti
    -1.48
    POSITIVE LOGITS
     to
    2.00
     but
    1.68
    if
    1.62
     ști
    1.52
     asegurar
    1.43
     исключительно
    1.39
    illant
    1.35
     and
    1.34
     ț
    1.34
     perfeito
    1.32
    Activations Density 0.261%

    No Known Activations