© 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. 70868
    Prev
    Next
    INDEX
    Explanations

    bicycle or ethyl compounds

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

    The neuron fires on occurrences of “bicycle” (and its close variants like bicycling or bicycles).

    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
    悒
    -2.89
    禤
    -2.53
    麴
    -2.47
    ⦊
    -2.41
     tallied
    -2.38
    瑧
    -2.38
    pierw
    -2.36
     ktoré
    -2.36
    甡
    -2.30
     אבל
    -2.27
    POSITIVE LOGITS
    橚
    2.88
    ”:
    2.73
     I
    2.73
     “
    2.69
     titulada
    2.67
    ”-
    2.66
      
    2.53
    This
    2.52
         
    2.44
    饹
    2.44
    Activations Density 0.012%

    No Known Activations