© 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. 22-GEMMASCOPE-RES-131K
    7. 104433
    Prev
    Next
    INDEX
    Explanations

    foreign language and symbols

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

    This neuron fires strongly on unusually long, multi-syllable words (i.e. tokens of high character length).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     możliwość
    -0.89
     berücksich
    -0.87
    の特徴
    -0.85
     paznok
    -0.84
     Osten
    -0.83
    教训
    -0.83
     Gaze
    -0.82
     Ähn
    -0.81
     美容
    -0.81
     früher
    -0.81
    POSITIVE LOGITS
    uchtigkeit
    1.13
    ọt
    0.97
     kwamba
    0.96
    -&
    0.95
     serangan
    0.94
    likation
    0.94
    ;&#
    0.94
    iennes
    0.93
    امية
    0.93
    🤮
    0.91
    Activations Density 0.036%

    No Known Activations