© 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. 102925
    Prev
    Next
    INDEX
    Explanations

    reborn dolls and prostheses

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

    This neuron responds to descriptive, sales-style language in toy product listings—particularly phrases about baby dolls and related children's playsets.

    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
    rect
    -0.74
     Coast
    -0.73
    riter
    -0.72
     Eier
    -0.70
     temporada
    -0.70
    ูป
    -0.70
    ást
    -0.70
    
    -0.69
    ровал
    -0.69
    ִּ
    -0.68
    POSITIVE LOGITS
     reborn
    0.98
    ését
    0.91
     vinyl
    0.87
     Reborn
    0.86
     realism
    0.86
     doll
    0.82
    ۇ
    0.82
     Boun
    0.80
    Aval
    0.80
     limbs
    0.78
    Activations Density 0.006%

    No Known Activations