© 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. 115721
    Prev
    Next
    INDEX
    Explanations

    not excessive

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

    The neuron responds to descriptive modifiers—intensifying adjectives and adverbs (e.g. “utmost,” “very,” “more,” “emotionally”) that signal degree or quality.

    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
    ophones
    -0.87
     ammat
    -0.84
    richTextBox
    -0.82
    BUL
    -0.81
    attractive
    -0.79
    ilization
    -0.79
    TTL
    -0.78
    IZATION
    -0.78
    ěla
    -0.78
    ybės
    -0.77
    POSITIVE LOGITS
     restraint
    3.17
     restrained
    3.02
     reserved
    2.88
     reserve
    2.42
     understated
    2.41
     Restra
    2.30
     restrain
    2.13
    reserved
    2.06
     understatement
    2.03
    Reserved
    1.99
    Activations Density 0.031%

    No Known Activations