© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91454
    Prev
    Next
    INDEX
    Explanations

    liquid level

    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
    Ȩ
    -0.79
    PIPE
    -0.77
    large
    -0.77
    LOCALE
    -0.75
    othed
    -0.74
    olar
    -0.73
     двери
    -0.73
    Longitude
    -0.73
    jela
    -0.73
    ğer
    -0.72
    POSITIVE LOGITS
     level
    3.11
     levels
    2.91
    level
    2.27
     уровня
    2.20
     уровень
    2.05
    levels
    2.02
     Levels
    2.00
    getLevel
    1.99
    Level
    1.95
     Level
    1.95
    Activations Density 0.034%

    No Known Activations