© 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. 10-GEMMASCOPE-RES-131K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    nose and following word

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

    The neuron activates on occurrences of the substring “nose.”

    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
    ですので
    -3.16
    >
    -2.94
    尛
    -2.92
     you
    -2.89
    ですが
    -2.88
     (“
    -2.75
    仉
    -2.72
    ですから
    -2.67
    :”
    -2.63
    掄
    -2.56
    POSITIVE LOGITS
    ᭡
    2.55
    翆
    2.50
     jones
    2.45
    裡的
    2.38
     italian
    2.28
     empathetic
    2.27
     obsessive
    2.22
    
    2.22
    Aç
    2.20
    𖣔
    2.20
    Activations Density 0.007%

    No Known Activations