© 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. 34-GEMMASCOPE-RES-131K
    7. 30097
    Prev
    Next
    INDEX
    Explanations

    programming constructs and methods

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

    The neuron activates on tokens that begin with a capital letter, i.e. capitalized words.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    getting
    -1.13
     getting
    -1.11
     gotten
    -1.08
     got
    -1.03
     Gets
    -0.99
    Gets
    -0.97
     bekam
    -0.96
     bekommen
    -0.94
     GETTING
    -0.91
     vôtre
    -0.90
    POSITIVE LOGITS
     access
    0.94
     –
    0.92
    </em>
    0.91
     find
    0.91
    msgstr
    0.84
    []
    0.83
     obtain
    0.82
    </i>
    0.81
     instance
    0.81
     make
    0.80
    Activations Density 0.001%

    No Known Activations