© 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. 59181
    Prev
    Next
    INDEX
    Explanations

    transient tic disorder

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

    section breaks or blank lines in text formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric date mentions—years and century markers (e.g. “1612,” “17th century”).

    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
    Intr
    -0.73
    ഴ
    -0.72
    glected
    -0.71
    irectional
    -0.70
    agrad
    -0.69
     Hildebrand
    -0.69
    SerializedName
    -0.68
    yeli
    -0.68
     Sandstone
    -0.68
     avto
    -0.68
    POSITIVE LOGITS
     Arthur
    1.04
     Salem
    0.92
     Abigail
    0.91
    Abigail
    0.85
     Putnam
    0.84
    Arthur
    0.84
     hysteria
    0.83
     flutes
    0.78
     McCarthy
    0.77
    loem
    0.77
    Activations Density 0.007%

    No Known Activations