© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93254
    Prev
    Next
    INDEX
    Explanations

    common phrases or collocations

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

    The neuron fires on mentions of Disney-branded vacation products and experiences (e.g. Disney Vacation Club, Disney Cruise Line, etc.).

    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
    сього
    -0.77
    poleon
    -0.75
     employee
    -0.75
    📭
    -0.75
     sexism
    -0.74
    cheerful
    -0.74
    angi
    -0.71
    retweet
    -0.70
    Переваги
    -0.69
     دين
    -0.69
    POSITIVE LOGITS
    hoty
    0.81
    /+
    0.81
     aidé
    0.79
     reservoirs
    0.77
    reserv
    0.77
    寿司
    0.77
     Reservoir
    0.76
     zul
    0.76
    Vì
    0.76
     -"
    0.75
    Activations Density 0.006%

    No Known Activations