© 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. 38524
    Prev
    Next
    INDEX
    Explanations

    Ecol, Ecotoxic, EcoBoost, evolution

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

    scientific and technical terminology related to ecology, biology, and product names with "eco" prefix.

    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
     trova
    -0.85
    شك
    -0.76
    waż
    -0.75
     проходит
    -0.75
    gesch
    -0.73
    本当の
    -0.72
     universality
    -0.69
    赐
    -0.69
     евре
    -0.69
     spare
    -0.69
    POSITIVE LOGITS
     Pisces
    0.78
    getDrawable
    0.75
     Shit
    0.75
    SRV
    0.75
    ùn
    0.74
     renown
    0.74
    ISF
    0.74
     clássico
    0.73
     vaid
    0.73
     侠
    0.73
    Activations Density 0.012%

    No Known Activations