© 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. 124035
    Prev
    Next
    INDEX
    Explanations

    first of april

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

    The neuron activates on the month name “April,” marking date references that include that specific month.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     It
    -2.73
    </strong>
    -2.45
     así
    -2.44
     станет
    -2.39
     are
    -2.36
    ’.
    -2.36
    ’
    -2.30
    ఽ
    -2.28
     ‘
    -2.27
    /
    -2.27
    POSITIVE LOGITS
    The
    3.38
    h
    3.22
    3
    3.14
    e
    3.13
    r
    2.84
    7
    2.83
    x
    2.78
    b
    2.77
    So
    2.77
    In
    2.77
    Activations Density 0.014%

    No Known Activations