© 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. 32363
    Prev
    Next
    INDEX
    Explanations

    polymerase chain reaction

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

    the term "chain reaction" in scientific or technical contexts.

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

    The neuron flags the first word in two‐word “… action” or “… reaction” compound phrases (e.g. “class action,” “chain reaction”).

    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
     inderdaad
    -0.81
     Diony
    -0.71
    مانی
    -0.70
     Fukuoka
    -0.70
    אָ
    -0.69
     الدن
    -0.68
    ColumnHeader
    -0.68
     Aula
    -0.68
    ställning
    -0.68
     TDP
    -0.67
    POSITIVE LOGITS
    mail
    1.40
     action
    1.37
     mail
    1.32
    action
    1.08
     Mail
    1.02
     MAIL
    1.02
    MAIL
    0.94
    Mail
    0.94
    ACTION
    0.92
     effect
    0.90
    Activations Density 0.092%

    No Known Activations