© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 28934
    Prev
    Next
    INDEX
    Explanations

    code imports and includes

    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
     
    -2.19
    0
    -2.02
    i
    -2.00
     asks
    -1.71
    2
    -1.70
    ”,
    -1.70
    n
    -1.66
     zweif
    -1.66
    },
    -1.66
     is
    -1.64
    POSITIVE LOGITS
     花纹
    1.95
     Quien
    1.93
     centru
    1.92
    vantaged
    1.90
    zös
    1.88
    ᯾
    1.88
    zja
    1.88
     occasione
    1.88
    dzić
    1.83
     Meilleur
    1.80
    Activations Density 0.017%

    No Known Activations