© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49224
    Prev
    Next
    INDEX
    Explanations

    Collins and Colin names

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

    The neuron is primarily triggered by named‐entity tokens—proper nouns (people, organizations, places) and numeric identifiers such as years or other numbers.

    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
    thereal
    -0.78
     своє
    -0.75
     spite
    -0.75
     весен
    -0.73
     empê
    -0.73
     проходит
    -0.73
     потрі
    -0.73
    리고
    -0.72
     Achter
    -0.72
    хоз
    -0.70
    POSITIVE LOGITS
    wood
    0.84
     Collins
    0.79
     hodin
    0.79
     rebu
    0.77
    expand
    0.75
     topographical
    0.74
    ⋃
    0.73
    ?");
    0.73
     демон
    0.73
    ilité
    0.72
    Activations Density 0.015%

    No Known Activations