© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1591
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

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

    This neuron detects parenthetical asides, i.e. text enclosed in or introduced by parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latter
    2.33
    后者
    1.64
     "),
    1.31
     ],
    1.22
     >,
    1.21
    ."),
    1.18
    `],
    1.17
    】,
    1.17
     】,
    1.13
    }^{+},
    1.11
    POSITIVE LOGITS
    )
    2.95
    ）
    2.30
    ')
    2.20
    ]
    2.14
    ")
    2.13
    ())
    2.13
    _)
    2.02
     )
    2.00
    }
    1.98
    ”)
    1.93
    Activations Density 0.308%

    No Known Activations