© 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. 59890
    Prev
    Next
    INDEX
    Explanations

    several items

    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
     seperti
    -2.48
    A
    -2.47
    At
    -2.16
    乍
    -2.00
    ]
    -1.97
    To
    -1.95
     Instead
    -1.93
    You
    -1.93
    In
    -1.91
     Geben
    -1.91
    POSITIVE LOGITS
    AutoresizingMask
    2.44
    TintMode
    2.41
    饜
    2.20
     málo
    2.14
     dozen
    2.14
    笮
    2.02
    稣
    2.02
    >
    2.00
    伷
    2.00
     hundred
    1.98
    Activations Density 0.007%

    No Known Activations