© 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. 23584
    Prev
    Next
    INDEX
    Explanations

    z-index, layer ordering

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

    The neuron is detecting numeric tokens (digits and numeric literals) 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
    Роз
    -0.79
    にかけて
    -0.79
    direction
    -0.74
     Himmels
    -0.73
    !');
    -0.73
    ﷻ
    -0.71
     роз
    -0.71
    平凡
    -0.69
    ་
    -0.69
    äsche
    -0.69
    POSITIVE LOGITS
     layer
    2.03
     foreground
    1.78
     LAYER
    1.75
     layers
    1.69
     Layer
    1.59
     depth
    1.58
     layering
    1.55
    Layer
    1.55
     behind
    1.44
     layered
    1.43
    Activations Density 0.042%

    No Known Activations