© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1800
    Prev
    Next
    INDEX
    Explanations

    numbering or bullet points

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

    This neuron detects list-item markers (bullets, asterisks, or numeric/parenthesized indices) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -3.28
     more
    -1.94
     only
    -1.80
     then
    -1.77
     or
    -1.73
     other
    -1.65
    Like
    -1.56
     також
    -1.52
     which
    -1.49
     all
    -1.48
    POSITIVE LOGITS
     to
    1.82
     }));
    1.63
    )};
    1.56
    //*[@
    1.52
     }).
    1.48
     })
    
    1.46
     thefe
    1.45
    DISCLAIMER
    1.41
    })();
    1.41
     ();
    1.41
    Activations Density 0.039%

    No Known Activations