© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15867
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks or parentheses

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

    The neuron activates on formal defined terms and key labeled items in legal or technical text (e.g. single-word labels in parentheses or quotes).

    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
    ”;
    1.24
    ";
    1.23
     ";
    1.17
    ]";
    1.16
    >";
    1.14
    /";
    1.14
    %";
    1.03
    `;
    1.02
    .";
    1.02
    !";
    1.02
    POSITIVE LOGITS
    ')
    1.93
    ")
    1.88
     ")
    1.79
    """)
    1.79
     ')
    1.77
    `)
    1.74
    ')}
    1.73
    .")
    1.70
    .')
    1.70
    !')
    1.69
    Activations Density 0.037%

    No Known Activations