© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69660
    Prev
    Next
    INDEX
    Explanations

    digit 2 following / * - or 1

    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
     to
    -2.50
    président
    -1.98
    château
    -1.84
     入っ
    -1.83
    日本的
    -1.82
    氏が
    -1.80
     participó
    -1.80
     sufrió
    -1.77
     yür
    -1.76
    氿
    -1.75
    POSITIVE LOGITS
    v
    2.78
    2
    2.77
    as
    2.64
    7
    2.55
    i
    2.39
    
    2.28
    g
    2.28
    8
    2.25
    I
    2.19
    e
    2.17
    Activations Density 0.028%

    No Known Activations