© 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. 73329
    Prev
    Next
    INDEX
    Explanations

    tree nodes and leaves

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

    This neuron fires on programming‐language tokens—identifiers (including CamelCase names), numeric literals, and other code symbols.

    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
     camels
    -0.76
    namb
    -0.74
    omnie
    -0.73
     Connelly
    -0.72
     estuaries
    -0.72
    perative
    -0.72
    inien
    -0.72
    irot
    -0.72
    Perd
    -0.72
    hadap
    -0.71
    POSITIVE LOGITS
     leaf
    3.50
     leaves
    3.08
    Leaf
    2.83
    leaf
    2.83
     Leaf
    2.70
     nodes
    2.56
     node
    2.50
    leaves
    2.31
     Leaves
    2.23
    LEAF
    2.16
    Activations Density 0.084%

    No Known Activations