© 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. 86721
    Prev
    Next
    INDEX
    Explanations

    perfect followed by suitability

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

    The neuron fires on positive promotional superlatives—especially the word “Perfect” and similar high-praise adjectives like “ideal,” “optimal,” or “great.”

    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
     instead
    -1.60
    ggiata
    -1.59
    instead
    -1.59
    2
    -1.56
    }
    -1.56
     促销
    -1.54
     wondrous
    -1.48
     白い
    -1.48
     alimentaria
    -1.47
    𨭎
    -1.47
    POSITIVE LOGITS
     for
    1.82
     your
    1.75
    You
    1.60
     if
    1.54
     seperti
    1.40
     an
    1.35
     seductive
    1.35
     epitom
    1.34
     During
    1.32
    Another
    1.32
    Activations Density 0.011%

    No Known Activations