© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10682
    Prev
    Next
    INDEX
    Explanations

    safety and reliability

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

    This neuron responds to occurrences of regular‐expression syntax (backslashes, character classes, quantifiers, grouping symbols, etc.).

    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
    }}\
    1.07
     }}\
    1.06
    ']]
    1.01
    ']])
    0.99
    "]]
    0.97
    ']}
    0.96
    ']],
    0.95
    ↵↵↵↵↵↵↵↵↵↵↵
    0.91
    】,
    0.90
    】
    0.89
    POSITIVE LOGITS
    </h4>
    2.97
    <h4>
    2.70
    )\\
    2.05
    .\\
    1.98
    )$\\
    1.95
    }\\
    1.95
    ).\\
    1.94
    $\\
    1.80
    ]\\
    1.80
    <h5>
    1.77
    Activations Density 0.033%

    No Known Activations