© 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. 10-GEMMASCOPE-RES-131K
    7. 69086
    Prev
    Next
    INDEX
    Explanations

    UIC UICollectionView

    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_10/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
     Importantly
    -3.11
     Historically
    -3.09
    囖
    -3.05
     Effectively
    -3.00
     algunas
    -2.98
    an
    -2.95
     Fifteen
    -2.91
     Extensive
    -2.88
    ：「
    -2.86
     Typical
    -2.83
    POSITIVE LOGITS
     apparence
    3.06
     itſelf
    3.05
    ם
    3.02
    苹
    2.83
    😚
    2.83
    豋
    2.81
     hjælp
    2.78
     tibur
    2.70
     tabac
    2.70
     decorativo
    2.70
    Activations Density 0.026%

    No Known Activations