© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71205
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs

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

    The neuron fires on strong emotion words (e.g. “gutted,” “delighted,” “overjoyed”) typically used to express a personal 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_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
     what
    -2.22
     our
    -2.09
     your
    -1.96
     staunch
    -1.95
     each
    -1.87
     prevent
    -1.86
     ayudar
    -1.86
     alleviate
    -1.86
     by
    -1.80
     every
    -1.80
    POSITIVE LOGITS
     œufs
    1.80
    }$,
    1.77
    越来越多
    1.75
    有种
    1.74
    ../../
    1.73
    齶
    1.72
    ꔹ
    1.71
    gucig
    1.70
     rigide
    1.69
     orale
    1.68
    Activations Density 0.015%

    No Known Activations