© 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. 34-GEMMASCOPE-RES-131K
    4. 83150
    Prev
    Next
    INDEX
    Explanations

    nomination or reprieve

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

    The neuron fires on any numeric token (digits or numbers, including version numbers and numeric literals).

    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
     Inti
    -0.72
    institution
    -0.71
     basil
    -0.65
    rabbitmq
    -0.65
    gloss
    -0.65
    ̥
    -0.63
     Gai
    -0.63
    Fixes
    -0.62
     насколько
    -0.60
     Auschwitz
    -0.60
    POSITIVE LOGITS
    filtered
    0.72
    ripe
    0.71
     repens
    0.71
     έναν
    0.70
     Sher
    0.69
    𝖻
    0.69
     pecados
    0.68
    Listener
    0.68
    lug
    0.67
    hall
    0.66
    Activations Density 0.075%

    No Known Activations