© 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. 83436
    Prev
    Next
    INDEX
    Explanations

    adjectives describing conditions

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

    The neuron fires on words that describe experimental or process conditions—especially adjectives and modifiers like “optimal,” “favorable,” “mild,” “ambient,” and the word “conditions” when specifying under‐what‐conditions statements.

    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
    𝙷
    -0.89
    beho
    -0.82
     foci
    -0.78
    cticide
    -0.77
    fauteuil
    -0.75
    撵
    -0.74
     歴史
    -0.73
    יוון
    -0.73
    nąć
    -0.73
     equidist
    -0.72
    POSITIVE LOGITS
     conditions
    7.41
    Conditions
    5.47
    conditions
    5.38
     Conditions
    5.28
     condiciones
    4.81
     CONDITIONS
    4.59
    条件
    4.31
     условия
    4.28
     condition
    4.03
    CONDITIONS
    3.88
    Activations Density 0.178%

    No Known Activations