© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73052
    Prev
    Next
    INDEX
    Explanations

    capitalized words followed by specific follow-ups

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

    The neuron predominantly fires on numeric tokens—especially page, volume, issue, or other decimal/integer references in citations and document metadata.

    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
    {
    -2.06
    鵟
    -1.95
    8
    -1.92
    Also
    -1.92
    
    -1.86
     propres
    -1.80
    鹀
    -1.80
     anhänger
    -1.77
    \.
    -1.75
    "
    -1.67
    POSITIVE LOGITS
    }$.
    2.09
    .”
    1.87
     if
    1.80
     they
    1.72
    砰
    1.70
    槃
    1.67
    )$;
    1.66
    }$,
    1.64
    chengladbach
    1.60
    )$,
    1.59
    Activations Density 0.000%

    No Known Activations