© 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. 93382
    Prev
    Next
    INDEX
    Explanations

    both X and Y

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

    The neuron fires on descriptive adverbs and adjectives (e.g. terms ending in –ly or –ic) that qualify experimental conditions, contexts, or modalities.

    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
     either
    -1.47
     both
    -1.33
     даже
    -1.20
     både
    -1.17
    both
    -1.14
    ];
    -1.12
    Either
    -1.06
     BOTH
    -1.05
     in
    -1.03
    either
    -1.02
    POSITIVE LOGITS
     thofe
    1.02
     аппетита
    1.02
     jacobs
    1.01
    selben
    0.99
    ichteten
    0.98
     glä
    0.95
     CENTRO
    0.93
     ภาพถ่าย
    0.93
     cereales
    0.91
     and
    0.91
    Activations Density 0.080%

    No Known Activations