© 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. 34-GEMMASCOPE-RES-131K
    7. 32962
    Prev
    Next
    INDEX
    Explanations

    half of a/an/the

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

    The main thing this neuron does is detect occurrences of the word “half.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    occupe
    -0.98
     Inseln
    -0.94
     greater
    -0.93
     part
    -0.90
     preparada
    -0.89
     кілька
    -0.88
     Rückkehr
    -0.87
     máte
    -0.87
     Schrifts
    -0.86
     same
    -0.84
    POSITIVE LOGITS
     of
    2.63
     the
    2.17
     دوباره
    0.99
    屑
    0.97
     menangkap
    0.93
     astuces
    0.92
     AGAIN
    0.91
     or
    0.90
     mengirimkan
    0.90
     as
    0.88
    Activations Density 0.012%

    No Known Activations