© 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. 99232
    Prev
    Next
    INDEX
    Explanations

    domains at a 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
    |<\
    -0.89
     tratti
    -0.82
    schema
    -0.79
    τερ
    -0.79
     набор
    -0.77
    lach
    -0.77
    óság
    -0.77
    螂
    -0.76
    ッセ
    -0.76
    rąg
    -0.75
    POSITIVE LOGITS
     level
    7.28
    level
    5.00
     levels
    4.28
    Level
    4.25
     Level
    4.13
    レベル
    4.06
     LEVEL
    3.98
     niveau
    3.88
    LEVEL
    3.88
     уровень
    3.72
    Activations Density 0.090%

    No Known Activations