© 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. 34-GEMMASCOPE-RES-131K
    7. 33267
    Prev
    Next
    INDEX
    Explanations

    irritable bowel

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

    HTML and XML document structure with specific focus on DOCTYPE declarations and URL paths.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on numeric tokens, i.e. sequences of digits.

    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
     half
    -0.75
     December
    -0.73
     seeing
    -0.72
    半个
    -0.70
     February
    -0.69
    addEdge
    -0.69
    dal
    -0.68
     alturas
    -0.67
    엇
    -0.66
     sees
    -0.66
    POSITIVE LOGITS
    Lava
    0.75
     Lava
    0.73
    บอล
    0.73
     Doncaster
    0.72
    buru
    0.71
     Zend
    0.68
     Socrates
    0.67
     therapeu
    0.67
     perl
    0.66
    Astronomy
    0.66
    Activations Density 0.124%

    No Known Activations