© 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. 34-GEMMASCOPE-RES-131K
    4. 65792
    Prev
    Next
    INDEX
    Explanations

    markup and code formatting

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

    The neuron selectively activates on numeric tokens (version numbers, section/problem numbers, citation keys, percentages, etc.).

    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
     croce
    -0.95
     other
    -0.87
     vettor
    -0.84
    lum
    -0.82
     luglio
    -0.80
    ber
    -0.78
     did
    -0.75
     cherokee
    -0.75
    並沒有
    -0.75
    不見
    -0.75
    POSITIVE LOGITS
    Minimal
    0.95
     dissertation
    0.84
    möbel
    0.84
    MITTED
    0.82
     Minimal
    0.82
    ouring
    0.80
    kämp
    0.79
     citi
    0.78
     {},
    0.75
    liato
    0.75
    Activations Density 0.002%

    No Known Activations