© 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. 110801
    Prev
    Next
    INDEX
    Explanations

    intra- prefix

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

    The neuron activates for scientific and technical terms beginning with "intra-" in academic and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ेश
    -0.79
    ]=\
    -0.70
    刁
    -0.70
    Partici
    -0.69
    ∓
    -0.69
    ご馳走
    -0.68
    fahrt
    -0.68
     humanas
    -0.67
    tley
    -0.67
     zur
    -0.66
    POSITIVE LOGITS
     intra
    5.91
    intra
    4.94
    Intra
    4.91
     Intra
    4.72
     внутри
    3.47
     intram
    3.02
     inter
    2.94
     internal
    2.75
     внутріш
    2.66
    internal
    2.42
    Activations Density 0.135%

    No Known Activations