© 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. 50152
    Prev
    Next
    INDEX
    Explanations

    Dr. Seuss stories

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

    The neuron fires on content‐bearing words—nouns, verbs, and adjectives that carry semantic meaning (especially less common or domain‐specific terms)—and stays silent on function words, numbers, and punctuation.

    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
     ferner
    -0.78
     αγ
    -0.71
     rilev
    -0.71
    Referring
    -0.71
     slapping
    -0.70
     Plow
    -0.69
     BCC
    -0.68
    asant
    -0.68
     приготов
    -0.68
    េ
    -0.66
    POSITIVE LOGITS
     Seuss
    1.77
     Dr
    1.52
    Dr
    1.23
     Horton
    1.11
     دکتر
    1.08
     Lor
    1.06
     Theodor
    1.06
    rhy
    1.04
    ландия
    0.90
    Lor
    0.88
    Activations Density 0.010%

    No Known Activations