© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43875
    Prev
    Next
    INDEX
    Explanations

    environmental impact statement

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

    The neuron identifies content related to environmental impact studies, assessments, and analyses.

    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_10/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
    けれ
    -1.57
    Selección
    -1.56
    /}{
    -1.50
    Despite
    -1.49
     erste
    -1.48
    zembro
    -1.42
    Edición
    -1.41
    不得不说
    -1.41
    Numerous
    -1.40
     說
    -1.39
    POSITIVE LOGITS
     zeer
    1.64
     nieuwe
    1.64
     they
    1.59
     consiste
    1.55
     planific
    1.53
     it
    1.51
     enorme
    1.50
     trois
    1.44
    слей
    1.41
     guru
    1.41
    Activations Density 0.013%

    No Known Activations