© 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. 34-GEMMASCOPE-RES-131K
    7. 49374
    Prev
    Next
    INDEX
    Explanations

    fuel additives and emissions

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

    technical content related to fuels, chemicals, and emissions in industrial contexts.

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

    The neuron is keyed to spotting numeric tokens and number‐like strings (e.g. years, digits, counts) in the text.

    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
     eviction
    -0.75
    nyata
    -0.69
     lietu
    -0.69
    タワー
    -0.69
     değ
    -0.66
    Frequency
    -0.66
    చు
    -0.66
    rored
    -0.66
    Bianca
    -0.65
    tabler
    -0.64
    POSITIVE LOGITS
     gasoline
    1.49
     MT
    1.19
     addi
    1.02
     additives
    1.02
     unle
    0.97
     Lea
    0.94
    Gasoline
    0.90
     Pelosi
    0.89
     reform
    0.88
    MT
    0.86
    Activations Density 0.045%

    No Known Activations