© 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. 103642
    Prev
    Next
    INDEX
    Explanations

    compression ignition engines

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

    The neuron primarily detects numeric tokens and numeric expressions (digits, numbers, and numeric punctuation).

    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
    Ан
    -0.73
    NNN
    -0.71
     mattresses
    -0.71
     Framework
    -0.69
    Ry
    -0.68
    rén
    -0.68
     framework
    -0.67
    Framework
    -0.66
     apreciar
    -0.66
    ريه
    -0.66
    POSITIVE LOGITS
    Compression
    1.17
     compression
    1.15
     pistons
    1.06
     Compression
    1.05
    jie
    0.88
    compression
    0.87
     static
    0.85
     ujednoznacz
    0.84
     Static
    0.83
    ratio
    0.82
    Activations Density 0.006%

    No Known Activations