© 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. 22-GEMMASCOPE-RES-131K
    7. 36563
    Prev
    Next
    INDEX
    Explanations

    judgment followed by reason

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

    The neuron fires on subjective evaluative words—adjectives and adverbs that express an opinion or judgment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Vernunft
    -1.05
     ilumina
    -1.00
    bunga
    -0.98
    Questa
    -0.96
     múltiple
    -0.95
     decorada
    -0.95
    此事
    -0.94
    rsiniz
    -0.93
    lägen
    -0.93
    pozdrawiam
    -0.93
    POSITIVE LOGITS
    !
    1.53
     because
    1.52
     since
    1.44
     considering
    1.42
     for
    1.41
     if
    1.22
     puisque
    1.13
    因为
    1.09
    ebly
    1.09
     поскольку
    1.02
    Activations Density 0.033%

    No Known Activations