© 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. 85160
    Prev
    Next
    INDEX
    Explanations

    repository context

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

    The neuron activates on occurrences of “repo” or “repos” (in any capitalization), i.e. tokens referring to software repositories.

    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
     \&
    -3.16
    ма
    -2.69
    }
    -2.55
     $
    -2.52
    ༀ
    -2.47
    {\
    -2.45
    と言
    -2.44
    
    -2.44
     tématu
    -2.41
     dreary
    -2.38
    POSITIVE LOGITS
    螄
    2.72
     officiels
    2.64
    鏨
    2.61
     estimés
    2.47
    何故
    2.47
    Because
    2.47
    ※※
    2.44
     padang
    2.41
    釭
    2.38
     melap
    2.36
    Activations Density 0.002%

    No Known Activations