© 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. 119486
    Prev
    Next
    INDEX
    Explanations

    biotinylated

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

    names like "Tanya" and technical terms ending in "ylated" like "biotinylated".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is a “name detector,” firing strongly on standalone proper names or name‐like tokens (e.g. Tanya, Netanya).

    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
     '
    -3.09
    
    -2.97
    I
    -2.70
    '
    -2.45
    但
    -2.31
     可以
    -2.22
    쩡
    -2.22
     
    -2.19
     klassische
    -2.19
    ان
    -2.19
    POSITIVE LOGITS
    ,’
    3.02
    .’
    2.89
    坼
    2.86
    洳
    2.81
    ﮩ
    2.78
    媜
    2.70
    
    2.53
    »،
    2.45
    岽
    2.41
    y
    2.39
    Activations Density 0.018%

    No Known Activations