© 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. 77556
    Prev
    Next
    INDEX
    Explanations

    data recording and acquisition

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

    The neuron strongly activates on terminology related to an aircraft crash investigation (e.g. “crashed,” “Air,” “jet,” “second black box,” “cockpit voice recorder”).

    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
     tantôt
    -0.78
    arj
    -0.75
    DBS
    -0.74
    polls
    -0.73
     BOW
    -0.73
    antique
    -0.73
     زده
    -0.73
    discuss
    -0.72
     comple
    -0.71
    清洁
    -0.71
    POSITIVE LOGITS
     recording
    2.22
     recorder
    1.94
     logger
    1.89
     data
    1.67
    logger
    1.66
     recordings
    1.66
     Recording
    1.66
     logging
    1.63
     Logger
    1.62
     recorders
    1.60
    Activations Density 0.030%

    No Known Activations