© 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. 79821
    Prev
    Next
    INDEX
    Explanations

    preparing for something

    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
    ↵
    -1.29
    \_
    -1.21
     compatible
    -1.16
    -
    -1.13
    k
    -1.13
    my
    -1.13
    for
    -1.12
     próprias
    -1.12
      
    -1.10
     иногда
    -1.10
    POSITIVE LOGITS
     the
    1.47
    柚子
    1.45
    蛧
    1.39
    蒾
    1.38
    äste
    1.31
     台北
    1.28
    Hermoso
    1.28
    inev
    1.26
    这
    1.23
    鳚
    1.21
    Activations Density 0.021%

    No Known Activations