© 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. 6791
    Prev
    Next
    INDEX
    Explanations

    intracellular or cranial

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

    anatomical and medical terminology related to cells and body structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specializes in detecting technical biomedical terms formed with Latin spatial or temporal prefixes (e.g. “intra-,” “extra-,” “perinatal-”).

    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
     Underworld
    -0.93
     ilang
    -0.84
     ANALYSIS
    -0.81
    ctiva
    -0.80
     cloche
    -0.79
     seguente
    -0.79
    OUNTS
    -0.79
     poucos
    -0.79
    зки
    -0.79
    瘣
    -0.79
    POSITIVE LOGITS
    mente
    1.08
    ly
    0.88
     space
    0.87
    ｮ
    0.83
     winning
    0.81
    mė
    0.81
    你了
    0.80
     but
    0.79
     location
    0.79
    空間
    0.79
    Activations Density 0.264%

    No Known Activations