© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99990
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    The neuron is detecting day‐of‐week tokens (e.g. “Tue,” “Wed,” “Mon”) in timestamp or date headers.

    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
    “
    -3.34
    “,
    -2.84
    ኧ
    -2.83
     Atención
    -2.70
    羮
    -2.70
    
    -2.63
    敺
    -2.53
    ”:
    -2.53
    <bos>
    -2.47
    ”;
    -2.45
    POSITIVE LOGITS
    1
    2.97
     của
    2.69
    '
    2.61
    ться
    2.53
     attaque
    2.52
     unquestionably
    2.48
    巔
    2.48
     '
    2.48
     של
    2.42
    责编
    2.41
    Activations Density 0.010%

    No Known Activations