© 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. 102938
    Prev
    Next
    INDEX
    Explanations

    verb followed by up

    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
     kän
    -0.75
     Aware
    -0.73
    俳
    -0.70
    ڱ
    -0.69
    鱧
    -0.69
    ᅲ
    -0.69
    ))=\
    -0.68
     häl
    -0.67
     beschikbaar
    -0.67
    inspirational
    -0.67
    POSITIVE LOGITS
     up
    0.94
    center
    0.82
     wal
    0.79
     dir
    0.74
    cosh
    0.73
    venia
    0.73
    HEX
    0.70
    𝕍
    0.70
    ugas
    0.69
    疼痛
    0.69
    Activations Density 0.024%

    No Known Activations