© 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. 33536
    Prev
    Next
    INDEX
    Explanations

    assemble and put together

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

    The neuron is highly responsive to numeric tokens and figures—i.e. it detects numbers and quantities in 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
    onade
    -0.83
    ornada
    -0.69
    Crawford
    -0.67
    liday
    -0.66
    tableCell
    -0.66
     Crawford
    -0.66
     Rewrite
    -0.66
     alap
    -0.66
    rigos
    -0.65
     rewritten
    -0.63
    POSITIVE LOGITS
     assembled
    5.56
     assemble
    5.47
     assembling
    5.31
     assembly
    5.09
     Assemble
    4.81
    assembled
    4.78
     assemb
    4.72
    assemble
    4.47
    Assemble
    4.44
     Assemb
    4.31
    Activations Density 0.197%

    No Known Activations