© 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. 89691
    Prev
    Next
    INDEX
    Explanations

    game states and configurations

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

    The neuron strongly activates on domain‐specific code and technical terms (e.g. class and variable names, function or board identifiers) within programming or math‐heavy 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
    ectos
    -0.94
    SCAL
    -0.84
    UNDE
    -0.79
    ∵
    -0.79
    stay
    -0.78
    squared
    -0.78
    longValue
    -0.77
    wiąz
    -0.77
     Pérez
    -0.77
    UNIT
    -0.75
    POSITIVE LOGITS
     state
    2.53
     configuration
    2.05
     situation
    1.95
     states
    1.91
     estado
    1.85
     situations
    1.75
    状态
    1.69
     configurations
    1.67
    state
    1.66
     currentState
    1.63
    Activations Density 0.018%

    No Known Activations