© 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. 102005
    Prev
    Next
    INDEX
    Explanations

    quiver, quinones, quiroga

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

    The neuron fires on the character sequence “qui” (e.g. in words like “qui,” “quiver,” “Quiñónez,” etc.).

    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
    1
    -3.48
    ti
    -2.94
    ]
    -2.73
    la
    -2.72
    т
    -2.59
    3
    -2.47
    c
    -2.45
     peculiar
    -2.44
     formidable
    -2.42
    ти
    -2.39
    POSITIVE LOGITS
    鶿
    2.83
    
    2.77
    嫆
    2.72
    
    2.59
    篭
    2.53
     restent
    2.52
    が行
    2.50
    がありますが
    2.48
    峮
    2.48
    acious
    2.47
    Activations Density 0.003%

    No Known Activations