© 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. 90467
    Prev
    Next
    INDEX
    Explanations

    European Spallation Source, Proton, run, source

    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
     adversity
    -0.75
     Dura
    -0.72
     --}}
    -0.71
    λογία
    -0.70
    lastIndexOf
    -0.70
    ensión
    -0.69
    ultas
    -0.69
     polling
    -0.68
     risk
    -0.68
     careers
    -0.67
    POSITIVE LOGITS
     BUB
    0.77
    ╭
    0.77
    °°
    0.75
    িক
    0.74
    ---|
    0.73
     NOISE
    0.73
     Halo
    0.73
    淡
    0.72
    ,-\
    0.71
     ASSISTANT
    0.70
    Activations Density 0.011%

    No Known Activations