© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    initiate, remove, or confront

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

    The neuron fires on the main verb of common colloquial phrasal verbs (e.g. kick, drop, hook, whip, knock, tear, screw).

    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
     where
    -2.03
     景点
    -1.82
     hırka
    -1.81
    bandicam
    -1.66
     leſs
    -1.62
    RemindMe
    -1.61
    諴
    -1.58
     when
    -1.55
    Deutsch
    -1.54
     zubehör
    -1.54
    POSITIVE LOGITS
     
    2.09
    ,”
    2.09
    ;
    1.80
            
    1.66
    núť
    1.61
     V
    1.59
     out
    1.56
    man
    1.55
    ‘
    1.55
    
    1.55
    Activations Density 0.119%

    No Known Activations