© 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. 34-GEMMASCOPE-RES-131K
    7. 118262
    Prev
    Next
    INDEX
    Explanations

    `.` followed by code constructs

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

    The neuron activates on sequences of digits, i.e. numeric literals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Fragen
    -0.92
     Memes
    -0.79
    enangan
    -0.78
    Inhalts
    -0.76
    pidou
    -0.75
     objectAtIndex
    -0.75
     algod
    -0.75
    Фар
    -0.74
    Hogyan
    -0.74
     ORDERED
    -0.74
    POSITIVE LOGITS
     include
    1.06
    include
    0.97
     color
    0.93
     font
    0.86
    color
    0.78
     textAlign
    0.78
     incluyen
    0.77
    inna
    0.77
     عالی
    0.75
     mùi
    0.75
    Activations Density 0.002%

    No Known Activations