© 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. 130470
    Prev
    Next
    INDEX
    Explanations

    entity descriptions and relationships

    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
    ."
    -2.41
    思议
    -2.31
     was
    -1.84
    ;
    -1.80
    ")
    -1.78
    。“
    -1.77
    菒
    -1.75
    禳
    -1.69
    </h5>
    -1.67
    g
    -1.66
    POSITIVE LOGITS
    Ꮉ
    2.17
     Because
    2.13
    ’，
    2.05
    迨
    2.05
    𖥧
    1.95
    賡
    1.91
    ܜ
    1.83
    噫
    1.71
     mewujudkan
    1.70
     integrante
    1.67
    Activations Density 0.013%

    No Known Activations