© 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. 34-GEMMASCOPE-RES-131K
    4. 91249
    Prev
    Next
    INDEX
    Explanations

    Baltimore Gas and Electric

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

    The neuron fires on the metadata header of news articles—author bylines, datelines, dates, and other structured information (names, places, and numbers) at the top of a story.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    });*/
    -0.76
     living
    -0.74
     koncentr
    -0.74
    的名
    -0.72
    leigh
    -0.71
    operatively
    -0.71
    endphp
    -0.71
    ೋ
    -0.70
    daya
    -0.69
    economia
    -0.68
    POSITIVE LOGITS
    itement
    0.86
     policemen
    0.75
     Plan
    0.71
    uinal
    0.71
     Leistungen
    0.71
     clipboard
    0.70
     endpoints
    0.69
    enen
    0.69
     yesterday
    0.66
     arco
    0.66
    Activations Density 0.025%

    No Known Activations