© 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. 76989
    Prev
    Next
    INDEX
    Explanations

    chemical science and analysis

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

    scientific research papers with chemical structures, compounds, or experimental methods.

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

    The neuron specializes in spotting numeric data (e.g. percentages, yields, and other numbers) in scientific 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
     uniform
    -0.83
    省
    -0.81
     such
    -0.77
     creation
    -0.75
    Creation
    -0.75
     just
    -0.73
    peq
    -0.73
     out
    -0.73
     escape
    -0.72
     identity
    -0.71
    POSITIVE LOGITS
     cytotoxicity
    0.96
    Tja
    0.94
     puer
    0.92
    🗄
    0.90
    IMPL
    0.90
     VLC
    0.89
     spectroscopic
    0.86
    França
    0.86
    Skal
    0.83
    gique
    0.82
    Activations Density 0.103%

    No Known Activations