© 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. 441
    Prev
    Next
    INDEX
    Explanations

    identification and typing

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

    scientific terminology in microbiology papers, particularly related to bacteria and lab techniques.

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

    The neuron fires on long technical or proper‐name phrases—especially multiword scientific titles or media/compound names.

    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
    Lundi
    -0.82
    сети
    -0.75
    tene
    -0.75
     flèche
    -0.74
    MLLoader
    -0.73
     בש
    -0.73
    یا
    -0.73
    alva
    -0.72
    urig
    -0.72
    RMS
    -0.71
    POSITIVE LOGITS
     production
    1.01
     Kov
    0.91
     Production
    0.86
     Reactions
    0.83
     reactions
    0.82
    production
    0.82
     biochemical
    0.81
    Biochemical
    0.79
     API
    0.78
     coag
    0.77
    Activations Density 0.066%

    No Known Activations