© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87083
    Prev
    Next
    INDEX
    Explanations

    return values, Ruby on Rails

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

    The neuron is selectively firing on numeric tokens (i.e. any standalone numbers or number-like strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     рост
    -0.82
     traer
    -0.77
     matéria
    -0.75
    )_{\
    -0.73
     honorary
    -0.71
    ことが
    -0.70
     menina
    -0.70
    topatho
    -0.69
     приводит
    -0.69
     menino
    -0.69
    POSITIVE LOGITS
     on
    1.22
    cadeira
    0.81
    投資
    0.77
    criminator
    0.77
     جمعیت
    0.75
    addVertex
    0.74
     Hoffmann
    0.73
     for
    0.73
    Laws
    0.73
    meteries
    0.73
    Activations Density 0.013%

    No Known Activations