© 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. 38306
    Prev
    Next
    INDEX
    Explanations

    inducing or causing effects

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

    The neuron selectively fires on specialized biomedical terms—especially those naming health conditions, biological sexes, immune/physiological processes, or disease-related entities.

    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
     zprá
    -0.84
    luiting
    -0.79
     onPostExecute
    -0.79
    cisme
    -0.77
    igata
    -0.76
    ៖
    -0.75
     inability
    -0.75
     berech
    -0.75
    hopper
    -0.75
    millan
    -0.74
    POSITIVE LOGITS
     generating
    2.14
     producing
    2.00
     inducing
    1.93
     enhancing
    1.68
    producing
    1.63
    inducing
    1.55
    generating
    1.53
     Generating
    1.43
    Generating
    1.35
     provoking
    1.32
    Activations Density 0.212%

    No Known Activations