© 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. 10-GEMMASCOPE-RES-131K
    7. 69206
    Prev
    Next
    INDEX
    Explanations

    chips, crackers, nachos

    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_10/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
    ie
    -1.87
     in
    -1.71
     albeit
    -1.70
     соединения
    -1.66
    although
    -1.52
    o
    -1.50
    er
    -1.47
    ↵
    -1.47
    A
    -1.44
    V
    -1.44
    POSITIVE LOGITS
    菝
    1.61
    ÇÃO
    1.58
    ResumeLayout
    1.48
    klärung
    1.48
     铝
    1.46
    ции
    1.44
     verminder
    1.43
    OpenAPI
    1.41
     først
    1.40
    rália
    1.40
    Activations Density 0.006%

    No Known Activations