© 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. 64654
    Prev
    Next
    INDEX
    Explanations

    closing brackets and parentheses

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

    The neuron detects tokens that look like code identifiers and literals (e.g. variable names and numbers) rather than natural-language words.

    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
     requires
    -1.02
     Requires
    -1.01
    requires
    -0.96
     includes
    -0.93
    Requires
    -0.89
     requiere
    -0.86
     Includes
    -0.86
    includes
    -0.84
    ))]
    -0.82
     incluye
    -0.79
    POSITIVE LOGITS
    )])
    1.61
    )})
    1.60
    }})
    1.47
    ]})
    1.45
    ]])
    1.43
    }])
    1.35
    )});
    1.24
    }});
    1.07
     came
    1.04
    ')))
    0.98
    Activations Density 0.026%

    No Known Activations