© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111588
    Prev
    Next
    INDEX
    Explanations

    Şahin Bey, Gesellschaft

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

    This neuron fires on tokens containing non-ASCII or accented characters (e.g. foreign names or words with diacritics).

    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
    </h3>
    -3.48
    ”
    -3.45
    s
    -3.27
    these
    -2.89
    鮠
    -2.83
    蚡
    -2.80
    the
    -2.73
      
    -2.58
    c
    -2.55
    by
    -2.53
    POSITIVE LOGITS
     It
    2.66
    存于
    2.50
     手機
    2.45
     內
    2.44
     變
    2.38
    enfone
    2.38
    曩
    2.38
     kterou
    2.34
    したこと
    2.28
     經
    2.28
    Activations Density 0.087%

    No Known Activations