© 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. 115627
    Prev
    Next
    INDEX
    Explanations

    code parsing and state

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

    The neuron strongly responds to code identifiers (e.g. variable, function, or field names) in source‐code snippets.

    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
    ТС
    -0.84
     gouverneur
    -0.81
     meuble
    -0.79
    hoga
    -0.79
     capitaine
    -0.79
     Misty
    -0.79
     espiritual
    -0.78
    ỏa
    -0.78
    idity
    -0.78
     УК
    -0.75
    POSITIVE LOGITS
     position
    1.39
     Position
    1.10
     remaining
    1.05
     current
    1.03
    Position
    1.01
     Current
    0.92
     uncons
    0.91
    剩余
    0.90
    current
    0.88
    Remaining
    0.88
    Activations Density 0.017%

    No Known Activations