© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69846
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

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

    This neuron detects hyphenated, intensifying compound adjectives (e.g. rock-hard, ice-cold, crystal-clear, lightning-fast).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ࿊
    -1.88
    狆
    -1.84
     málo
    -1.76
    𝕿
    -1.71
    ↵↵
    -1.70
    詬
    -1.68
    廝
    -1.67
    struzioni
    -1.66
    鸰
    -1.66
    起来的
    -1.61
    POSITIVE LOGITS
     of
    2.42
    //
    2.05
    while
    1.80
    Another
    1.76
    There
    1.76
    ・・・・・
    1.75
    Other
    1.70
    just
    1.68
     desire
    1.67
    Also
    1.66
    Activations Density 0.024%

    No Known Activations