© 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. 91282
    Prev
    Next
    INDEX
    Explanations

    ticket prices, regulation, company names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cinema
    -0.79
     reservations
    -0.77
     características
    -0.77
     film
    -0.75
     nights
    -0.75
     zelfs
    -0.75
    IfNeeded
    -0.73
     concessions
    -0.71
    招生
    -0.70
     Reservations
    -0.69
    POSITIVE LOGITS
    DIST
    0.88
    sic
    0.88
     Konink
    0.81
    ༘
    0.79
    __':
    0.78
    Dissertation
    0.77
    langs
    0.76
    according
    0.75
     morphine
    0.74
    citi
    0.74
    Activations Density 0.016%

    No Known Activations