© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3030
    Prev
    Next
    INDEX
    Explanations

    preferential incorporation and synthesis

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

    scientific text describing biological or chemical processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens (quantities, measurements, or other numbers) 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
    getJSONObject
    -0.82
    𝗼
    -0.75
    lardır
    -0.75
    이크
    -0.74
    atiles
    -0.73
    âce
    -0.73
    dataflow
    -0.73
    evalu
    -0.73
    ekte
    -0.72
    után
    -0.71
    POSITIVE LOGITS
     binding
    1.10
     synthesize
    1.05
     bind
    1.03
     synthesis
    1.00
    binding
    0.98
     synthe
    0.98
    ‛
    0.96
    synthe
    0.95
    Binding
    0.94
     incorporation
    0.93
    Activations Density 0.284%

    No Known Activations