© 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. 25540
    Prev
    Next
    INDEX
    Explanations

    species, flora, fauna, variety

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

    paragraphs describing wildlife and biodiversity in natural areas.

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

    The main thing this neuron does is spot numerical and quantitative data—like counts, years, measurements, and other number‐related information.

    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
     cities
    -1.05
    衞
    -0.98
     or
    -0.94
     powsta
    -0.93
     it
    -0.91
     after
    -0.90
    べる
    -0.90
     for
    -0.90
    farmer
    -0.90
     countries
    -0.88
    POSITIVE LOGITS
     rare
    1.87
     species
    1.76
     fauna
    1.52
     variety
    1.39
    rare
    1.37
     flora
    1.36
     rarer
    1.28
     varieties
    1.26
     resident
    1.25
    Rare
    1.25
    Activations Density 0.039%

    No Known Activations