© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67866
    Prev
    Next
    INDEX
    Explanations

    holiday events and listings

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

    The neuron strongly activates on numeric tokens (digits, measurements, years, percentages) and other number-like expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     okaz
    -0.95
     location
    -0.84
    で開催
    -0.83
    ないです
    -0.82
    mology
    -0.81
     users
    -0.81
    前は
    -0.78
     Catedral
    -0.78
     gdy
    -0.77
    UILabel
    -0.77
    POSITIVE LOGITS
     concomitant
    1.07
     accompanying
    1.02
    tadiene
    0.85
     simultaneous
    0.84
     samtidig
    0.83
    цыя
    0.79
    radical
    0.78
     艺术
    0.78
     Autumn
    0.75
     hymns
    0.75
    Activations Density 0.079%

    No Known Activations