© 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. 7056
    Prev
    Next
    INDEX
    Explanations

    closing brackets sequences

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

    This neuron strongly activates on numeric constants and related arithmetic operators in code (e.g., standalone numbers like “2” or operators “+”, “*”).

    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
    ]);
    1.00
    ));
    0.98
    ))
    0.97
    ),
    0.95
    });
    0.95
    ),]
    0.93
    ),"
    0.92
    })
    0.89
    ],
    0.87
    ])
    0.86
    POSITIVE LOGITS
    }}}\
    0.94
    exactly
    0.89
     EXACT
    0.86
     exactly
    0.85
    exact
    0.82
    }}}}
    0.82
     esattamente
    0.79
     Exact
    0.79
     exact
    0.78
    Exactly
    0.78
    Activations Density 0.004%

    No Known Activations