© 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. 14614
    Prev
    Next
    INDEX
    Explanations

    Québec, analgesia, WebSocket

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

    The neuron is triggered by tokens containing non-ASCII or foreign-script characters (e.g. accented letters or Cyrillic).

    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
    also
    -3.06
    也要
    -2.92
    at
    -2.84
    s
    -2.81
    on
    -2.61
    u
    -2.58
    r
    -2.56
     Also
    -2.53
    也会
    -2.47
    也很
    -2.47
    POSITIVE LOGITS
     ausein
    2.67
    各样的
    2.59
     یا
    2.56
    蟶
    2.48
    吓得
    2.44
    𝐒
    2.42
    锱
    2.39
     captivated
    2.38
    都已经
    2.36
    
    2.36
    Activations Density 0.014%

    No Known Activations