© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101461
    Prev
    Next
    INDEX
    Explanations

    mythological names and programming terms

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

    proper nouns, particularly brand names, product names, and place names.

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

    The neuron activates on capitalized named entities and acronyms (proper nouns).

    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
    𝘙
    -2.53
    h
    -2.50
    ations
    -2.44
    偌
    -2.42
    もしれません
    -2.39
    ⦊
    -2.38
     knows
    -2.33
     mencionado
    -2.31
     they
    -2.27
     страх
    -2.27
    POSITIVE LOGITS
    2.66
    3
    2.56
    2
    2.50
    
    2.36
     يمكنك
    2.27
     are
    2.22
    4
    2.22
    䥑
    2.20
    ŚĆ
    2.20
     花朵
    2.20
    Activations Density 0.020%

    No Known Activations