© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72650
    Prev
    Next
    INDEX
    Explanations

    please log in

    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
    躂
    -2.41
    %;
    -2.30
     fantasmas
    -2.25
     pilares
    -2.16
     {
    -2.05
     núcleos
    -2.02
    หรือ
    -1.96
     hinder
    -1.91
     尔
    -1.88
    怄
    -1.86
    POSITIVE LOGITS
    2
    2.28
    ↵
    2.03
    0
    2.02
    3
    1.78
    na
    1.77
     zahlreichen
    1.72
    龊
    1.71
    1
    1.66
    with
    1.65
     aumenta
    1.59
    Activations Density 0.002%

    No Known Activations