© 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. 119229
    Prev
    Next
    INDEX
    Explanations

    URL, file paths, and academic citations

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

    The neuron primarily detects numeric tokens—especially multi‐digit numbers in dates and timestamps.

    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
    omore
    -0.96
    plar
    -0.86
     Vries
    -0.84
    fea
    -0.84
     wenig
    -0.82
     anderer
    -0.81
    WRITER
    -0.77
     railroad
    -0.77
    inys
    -0.77
     Nin
    -0.77
    POSITIVE LOGITS
    ÈRE
    0.93
    需
    0.85
    Én
    0.81
    𓏸
    0.80
    ⎨
    0.78
     bibir
    0.78
    Fullscreen
    0.77
     notor
    0.76
    lacement
    0.76
     kesi
    0.75
    Activations Density 0.005%

    No Known Activations