© 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. 23862
    Prev
    Next
    INDEX
    Explanations

    di, bis, benz prefixes

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

    chemical notation for molecular compounds, especially numbers followed by commas, hyphens, or chemical prefixes.

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

    The neuron activates on numeric tokens—especially digits that form part of chemical compound identifiers or numeric designations.

    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
    整天
    -0.90
     tersedia
    -0.88
     one
    -0.87
     problems
    -0.83
     ditawarkan
    -0.82
    ارع
    -0.81
     disediakan
    -0.81
     diterapkan
    -0.81
    不但
    -0.81
    CEEDED
    -0.79
    POSITIVE LOGITS
    Bis
    1.04
     duo
    0.99
    bis
    0.94
     pair
    0.93
    dimethyl
    0.88
    ATHER
    0.86
    Pairs
    0.84
    Explain
    0.84
    dide
    0.84
     duet
    0.83
    Activations Density 0.065%

    No Known Activations