© 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. 82520
    Prev
    Next
    INDEX
    Explanations

    Bose-Einstein condensation

    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
     ORDERED
    -0.72
     motionless
    -0.64
     coisa
    -0.64
     molds
    -0.63
     evidenced
    -0.63
     мі
    -0.63
     Lizzy
    -0.62
    ├
    -0.62
     aforementioned
    -0.62
     mansions
    -0.61
    POSITIVE LOGITS
    tillon
    0.75
    chess
    0.71
     illegal
    0.71
    setBlock
    0.71
    Sleeping
    0.71
    mongoose
    0.70
     Sleeping
    0.69
    晶
    0.69
     повече
    0.69
     sleeping
    0.69
    Activations Density 0.068%

    No Known Activations