© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13675
    Prev
    Next
    INDEX
    Explanations

    closing html/xml tags

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

    The main thing this neuron does is identify URLs and hyperlink markup (e.g. “http://”, “www.”, “url=”, anchor tags, domain names).

    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
    <start_of_image>
    1.34
    }\\
    0.58
     \}
    0.57
     }>
    0.57
     }}>
    0.53
     हुईं
    0.50
     >;
    0.50
    tabPage
    0.48
    ']>
    0.48
    }->
    0.48
    POSITIVE LOGITS
    </
    2.14
    ?</
    2.08
    !</
    2.05
    )</
    2.03
     </
    1.99
    ).</
    1.95
    .</
    1.94
    /</
    1.90
    。</
    1.86
    "</
    1.85
    Activations Density 0.025%

    No Known Activations