© 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. 10-GEMMASCOPE-RES-131K
    7. 86630
    Prev
    Next
    INDEX
    Explanations

    line

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

    The neuron activates on error messages and stack‐trace lines (e.g. “Traceback”, “Warning”, exception dumps).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ”
    -2.27
    clerosis
    -1.94
    izoen
    -1.64
     ensure
    -1.55
    ’
    -1.53
    ]))
    -1.51
     rely
    -1.51
     believe
    -1.50
    gypti
    -1.49
    lgari
    -1.46
    POSITIVE LOGITS
    苙
    1.96
     determinados
    1.90
    The
    1.88
    乄
    1.85
    "
    1.79
    怍
    1.77
    '
    1.77
    D
    1.76
    ኵ
    1.76
     distintos
    1.75
    Activations Density 0.002%

    No Known Activations