© 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. 105332
    Prev
    Next
    INDEX
    Explanations

    centuries BCE AD CE BC

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

    This neuron fires on short uppercase abbreviations (like “ACP,” “Auto,” “CE,” etc.), i.e. brief all-caps tokens often used as units, model codes, or era markers.

    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
     }));
    -1.58
    })),
    -1.51
    #(
    -1.49
    "});
    -1.47
    푔
    -1.46
    ÃO
    -1.45
    ates
    -1.41
    镡
    -1.38
     shopee
    -1.38
    CEAN
    -1.38
    POSITIVE LOGITS
     result
    1.65
     Ergebnis
    1.41
     '
    1.38
     bereits
    1.38
    ↵
    1.33
     результат
    1.31
     takiej
    1.28
    ↵↵
    1.27
     Along
    1.27
    งาน
    1.23
    Activations Density 0.053%

    No Known Activations