© 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. 104898
    Prev
    Next
    INDEX
    Explanations

    web development code snippets

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

    variable or property names related to text content or status in API responses and code (like "responseText", "statusText", and positioning attributes such as "xpos", "ypos", "paddingLeft").

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

    The neuron activates on numeric literals (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
     from
    -3.02
     unrelenting
    -3.02
     exuberant
    -2.97
     poignant
    -2.91
     sehr
    -2.70
     longstanding
    -2.61
     burgeoning
    -2.61
     inadequate
    -2.56
     overtly
    -2.55
     exquisite
    -2.53
    POSITIVE LOGITS
    鵙
    3.16
    actéristi
    2.86
     EIGHT
    2.77
     accentu
    2.75
    雠
    2.72
     テープ
    2.72
     zoude
    2.72
    泐
    2.69
    
    2.67
     SEVEN
    2.64
    Activations Density 0.001%

    No Known Activations