© 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. 8606
    Prev
    Next
    INDEX
    Explanations

    The neuron detects web links and URL components (e.g. “http://”, domain names, path segments, and file extensions).

    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
     stain
    0.94
     staining
    0.93
     )
    0.86
     stains
    0.85
     stained
    0.82
     ).
    0.76
     );
    0.75
     Stain
    0.75
     ),
    0.71
    </td>
    0.71
    POSITIVE LOGITS
    >,
    1.57
    >;
    1.46
    >.
    1.45
    >",
    1.40
    >:
    1.39
    >]
    1.34
    >(
    1.34
     >,
    1.33
    >}
    1.31
    >
    1.27
    Activations Density 0.021%

    No Known Activations