© 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. 92519
    Prev
    Next
    INDEX
    Explanations

    presence, absence, and addition of substances

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

    scientific descriptions of experimental treatments in research papers, particularly involving chemicals, drugs, or compounds.

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

    The neuron activates on numeric tokens, i.e. it detects numbers (quantitative values) 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
    шы
    -0.84
     Schul
    -0.82
     маса
    -0.82
    lamino
    -0.79
    出手
    -0.78
    körper
    -0.77
    捩
    -0.76
    のように
    -0.76
    tbl
    -0.75
    Effort
    -0.75
    POSITIVE LOGITS
     concentrations
    2.02
     concentration
    1.88
     Concentrations
    1.52
    concentr
    1.45
    Concentration
    1.41
     concentración
    1.31
     addition
    1.26
     Concentration
    1.21
    concentration
    1.17
     концентра
    1.17
    Activations Density 0.374%

    No Known Activations