© 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. 6839
    Prev
    Next
    INDEX
    Explanations

    events unfolding

    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
     tiếng
    -0.92
    hoots
    -0.90
     Existence
    -0.75
    eland
    -0.73
    cyte
    -0.73
    )|(
    -0.71
     spä
    -0.71
    xlsx
    -0.70
    ForType
    -0.70
    hoot
    -0.69
    POSITIVE LOGITS
     unfold
    4.69
     unfolds
    4.47
     unfolding
    4.47
     unfolded
    4.31
     unravel
    2.03
     развер
    2.03
    展开
    2.00
    展開
    1.95
    folding
    1.82
     dérou
    1.71
    Activations Density 0.047%

    No Known Activations