© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83865
    Prev
    Next
    INDEX
    Explanations

    past followed by words

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

    The neuron is triggered by the preposition “past,” strongly activating on occurrences of the word “past.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     "
    -2.64
     
    -2.58
    .
    -2.56
     is
    -2.42
      
    -2.41
    ка
    -2.30
    the
    -2.23
     $
    -2.13
    \
    -2.11
    –
    -2.02
    POSITIVE LOGITS
    تیجه
    2.80
    jednoc
    2.39
     the
    2.39
    ława
    2.27
    珦
    2.19
    𓆟
    2.17
     akhirnya
    2.13
    各种
    2.11
    презента
    2.11
    年に
    2.09
    Activations Density 0.007%

    No Known Activations