© 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. 10-GEMMASCOPE-RES-131K
    7. 102413
    Prev
    Next
    INDEX
    Explanations

    circa or scientific names

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

    The neuron detects the abbreviation "ca." which typically stands for "circa" or "approximately" when referring to dates or measurements.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    踽
    -3.16
    zembro
    -3.03
    ꦢ
    -2.98
    鲧
    -2.89
    髕
    -2.84
    谞
    -2.84
    衪
    -2.83
    辚
    -2.81
     ,‬
    -2.80
    疴
    -2.80
    POSITIVE LOGITS
     '
    3.11
    _
    3.08
    The
    2.81
    {
    2.69
     `
    2.66
    ]
    2.61
     was
    2.58
    )
    2.58
    At
    2.50
    9
    2.50
    Activations Density 0.003%

    No Known Activations