© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101961
    Prev
    Next
    INDEX
    Explanations

    email recipients

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

    whitespace characters, particularly tabs and multiple consecutive spaces used for indentation or formatting in code and structured documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is primarily triggered by numeric tokens (integers or floating-point 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
     estadounidense
    -1.76
     Founded
    -1.66
    ceptos
    -1.61
    ?"
    -1.58
    その他
    -1.57
    O
    -1.56
    ଝ
    -1.55
    .'
    -1.54
     என்ற
    -1.52
    ското
    -1.52
    POSITIVE LOGITS
    adverti
    1.55
    Espace
    1.52
     lyder
    1.52
    㩒
    1.52
    Veuillez
    1.50
    tığı
    1.47
    Votre
    1.44
    Программа
    1.43
    Niveau
    1.42
    vantaged
    1.41
    Activations Density 0.195%

    No Known Activations