© 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. 38324
    Prev
    Next
    INDEX
    Explanations

    image data, luminance signal

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

    The neuron fires on numeric tokens (digits, numbers, and alphanumeric codes containing digits) in the text.

    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
    jon
    -0.88
    ᅢ
    -0.81
    主婦
    -0.81
    ือก
    -0.75
    詞
    -0.75
    inko
    -0.73
    CONFLICT
    -0.69
     όμως
    -0.69
    collide
    -0.68
    tamine
    -0.68
    POSITIVE LOGITS
     chroma
    1.10
     Cr
    0.93
     Costello
    0.90
     subs
    0.89
     Sampling
    0.86
    Sampling
    0.86
     sắc
    0.85
     skin
    0.85
     Burnett
    0.84
    Cr
    0.83
    Activations Density 0.038%

    No Known Activations