© 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. 22-GEMMASCOPE-RES-131K
    7. 73847
    Prev
    Next
    INDEX
    Explanations

    energy superpower or storage

    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_22/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
    '
    -2.98
    甗
    -2.94
     USING
    -2.92
     ハート
    -2.73
    of
    -2.72
    ’
    -2.66
    ホント
    -2.59
     VERY
    -2.55
    僰
    -2.50
     dando
    -2.48
    POSITIVE LOGITS
     of
    3.80
     strives
    2.64
    淦
    2.58
    誊
    2.50
     \
    2.44
    訛
    2.44
    ～～
    2.42
     After
    2.38
    って思
    2.38
     Not
    2.36
    Activations Density 0.023%

    No Known Activations