© 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. 110806
    Prev
    Next
    INDEX
    Explanations

    programming keywords

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

    whitespace indentation at the beginning of lines in code, particularly in Java source files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on floating‐point numeric literals (decimal numbers) in code.

    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
    珦
    -2.08
    鸸
    -1.88
     adecu
    -1.83
     recomendable
    -1.82
     estrena
    -1.77
     Tienen
    -1.73
    
    -1.71
     prevé
    -1.70
     presentará
    -1.70
    が違う
    -1.69
    POSITIVE LOGITS
     of
    2.06
    8
    1.62
     support
    1.61
    1
    1.53
    「
    1.52
    0
    1.52
    },
    1.47
    4
    1.46
    }
    1.45
    2
    1.45
    Activations Density 0.006%

    No Known Activations