© 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. 107585
    Prev
    Next
    INDEX
    Explanations

    United States, Nationals, Sal

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

    The neuron is looking for unusual or content-rich tokens—rare words and proper nouns that carry high information content.

    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
    稲荷
    -0.83
     A
    -0.80
    ĩ
    -0.78
    ˜
    -0.77
     move
    -0.77
     "
    -0.76
     Human
    -0.75
    <h2>
    -0.74
     ICommand
    -0.74
    may
    -0.73
    POSITIVE LOGITS
     CLIMATE
    1.02
    Climate
    0.94
    ällt
    0.93
     farmacia
    0.90
     klimat
    0.90
     cyclisme
    0.87
     sprites
    0.87
     Climate
    0.86
     Capcom
    0.86
     pascua
    0.85
    Activations Density 0.001%

    No Known Activations