© 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. 10-GEMMASCOPE-RES-131K
    7. 111114
    Prev
    Next
    INDEX
    Explanations

    dialogue and interaction

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

    The neuron fires on words referring to conversational exchange—especially “dialog,” “dialogue,” “conversation,” and related forms.

    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
    untuk
    -2.05
    ’
    -1.84
     who
    -1.79
    磲
    -1.69
    ↵
    -1.67
    鍏
    -1.66
    tığı
    -1.65
    </h2>
    -1.63
    ),
    -1.60
    sprechend
    -1.60
    POSITIVE LOGITS
     OGSÅ
    1.89
    èdent
    1.81
    ܜ
    1.76
     插画
    1.68
    In
    1.62
     these
    1.60
     marinho
    1.58
    镔
    1.54
     étroite
    1.54
    潾
    1.50
    Activations Density 0.014%

    No Known Activations