© 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. 65166
    Prev
    Next
    INDEX
    Explanations

    models, modules, neurons, examples

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

    This neuron activates on longer content words—i.e. tokens noticeably longer than typical function words.

    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
    Rozm
    -0.83
    webElementGuid
    -0.75
     تنها
    -0.72
     صفر
    -0.71
     uống
    -0.71
    ⃝
    -0.71
     Goodness
    -0.70
     affection
    -0.69
    Goed
    -0.69
     Decorate
    -0.69
    POSITIVE LOGITS
     situations
    0.72
    ായി
    0.71
    zondere
    0.71
     sytu
    0.70
     Includes
    0.70
    LastName
    0.69
    ลักษ
    0.68
    rapnel
    0.68
    ()));
    0.68
    inelli
    0.68
    Activations Density 0.040%

    No Known Activations