© 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. 6785
    Prev
    Next
    INDEX
    Explanations

    chef, restaurant, award, personality

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

    This neuron activates on capitalized proper names and titles (e.g. award names, brand and show titles).

    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
     Agile
    -0.87
     cont
    -0.85
    下山
    -0.83
     vegan
    -0.82
     Precipitation
    -0.79
     neuros
    -0.78
     интер
    -0.77
     agile
    -0.76
    umahan
    -0.76
     taş
    -0.76
    POSITIVE LOGITS
     inol
    0.85
     amerik
    0.83
     lunedì
    0.82
     desir
    0.82
     personnels
    0.80
     poft
    0.79
     pandora
    0.76
     noft
    0.76
    RESTAUR
    0.76
     applau
    0.75
    Activations Density 0.012%

    No Known Activations