© 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. 103802
    Prev
    Next
    INDEX
    Explanations

    great

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

    The neuron fires on the hyperbolic descriptive adjectives (and related wording) you’d find in real‐estate or home‐tour copy—words that emphasize spaciousness, grandeur, and luxury.

    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
     grandma
    -0.81
    谑
    -0.78
     Modific
    -0.76
     vych
    -0.76
     provoca
    -0.75
    自体は
    -0.74
    erts
    -0.73
    bind
    -0.73
     Grandmother
    -0.72
     SAID
    -0.71
    POSITIVE LOGITS
     great
    4.66
    great
    3.84
    Great
    3.66
     Great
    3.56
     GREAT
    2.78
    GREAT
    2.73
     вели
    2.48
    Вели
    1.91
     greats
    1.83
     Вели
    1.74
    Activations Density 0.010%

    No Known Activations