© 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. 85148
    Prev
    Next
    INDEX
    Explanations

    commonly, typically

    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
     and
    -1.89
     is
    -1.77
     kemudian
    -1.71
    sena
    -1.62
    ℟
    -1.60
    sider
    -1.55
    icona
    -1.52
    镕
    -1.51
     
    -1.50
    
    -1.50
    POSITIVE LOGITS
    f
    2.30
    a
    2.09
    b
    2.02
    c
    1.98
    ”
    1.94
    m
    1.90
    }$,
    1.86
    本日の
    1.81
     actriz
    1.80
    にほんブログ村
    1.78
    Activations Density 0.062%

    No Known Activations