© 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. 103665
    Prev
    Next
    INDEX
    Explanations

    census data

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

    The neuron chiefly responds to numeric tokens (i.e. numbers and years) 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_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
     auctions
    -0.83
     vendors
    -0.77
    SimpleName
    -0.77
     beim
    -0.74
     Zusch
    -0.74
     عالی
    -0.73
     weddings
    -0.73
    怪物
    -0.72
     रही
    -0.72
    oric
    -0.71
    POSITIVE LOGITS
    yní
    0.89
    Manuscript
    0.79
     Manuscript
    0.74
     Marcello
    0.73
     Specialties
    0.72
    తి
    0.71
     交
    0.71
    ße
    0.71
     Schedules
    0.71
     Microphone
    0.70
    Activations Density 0.022%

    No Known Activations