© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58903
    Prev
    Next
    INDEX
    Explanations

    Wild Barrel beer and products

    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
    それとも
    -0.73
     universal
    -0.72
     Original
    -0.72
    histogram
    -0.71
     Mlle
    -0.71
     unsatisfactory
    -0.71
     papi
    -0.71
     Manly
    -0.71
     Bottom
    -0.71
    Bottom
    -0.69
    POSITIVE LOGITS
     lactose
    1.01
    Bret
    0.99
     barrel
    0.96
     sour
    0.96
     Bret
    0.92
    Barrel
    0.88
     aged
    0.86
     Aged
    0.83
    Collaboration
    0.83
     Collaboration
    0.82
    Activations Density 0.013%

    No Known Activations