© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13481
    Prev
    Next
    INDEX
    Explanations

    occurrences and time periods

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

    The neuron selectively activates on the word “times.”

    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
     (‘
    -2.61
    愎
    -2.58
     levando
    -2.55
    ,”
    -2.42
     ”
    -2.42
     ‘
    -2.36
     I
    -2.30
    ”(
    -2.28
    名を
    -2.28
    lgari
    -2.27
    POSITIVE LOGITS
    u
    3.58
    times
    2.92
    )
    2.78
    訁
    2.59
     समीक्षाएं
    2.56
    le
    2.52
     IBOutlet
    2.50
    örté
    2.45
     we
    2.42
     ส์
    2.41
    Activations Density 0.018%

    No Known Activations