© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116358
    Prev
    Next
    INDEX
    Explanations

    code comments and file headers

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

    The neuron fires on assignment‐style separators in code or config lines—i.e. tokens like “=”, “:”, and numeric values that appear in key–value pairs.

    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
     percol
    -0.82
    interactions
    -0.78
    latego
    -0.74
     signaling
    -0.70
     Interaction
    -0.68
     diffuser
    -0.68
    Interactions
    -0.66
     Signaling
    -0.66
     जीवन
    -0.65
    regado
    -0.65
    POSITIVE LOGITS
    axs
    0.66
     Kämp
    0.64
    Steven
    0.64
    tich
    0.63
     piedras
    0.63
     specification
    0.63
    ouest
    0.62
    amata
    0.61
    Deque
    0.61
    DisplayName
    0.61
    Activations Density 0.061%

    No Known Activations