© 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. 34-GEMMASCOPE-RES-131K
    7. 117501
    Prev
    Next
    INDEX
    Explanations

    je, jee, ye, or words starting with 'je'

    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_34/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
    merksamkeit
    -0.86
    人形
    -0.77
    man
    -0.76
    足够
    -0.75
    Original
    -0.74
    没有
    -0.69
     Descri
    -0.69
    凡
    -0.68
     Prozent
    -0.68
     is
    -0.68
    POSITIVE LOGITS
    glicher
    0.94
    jeli
    0.87
    elry
    0.85
    tison
    0.84
     kompleks
    0.84
     néanmoins
    0.84
     CLK
    0.83
    kies
    0.81
    ensione
    0.81
    شاركة
    0.80
    Activations Density 0.018%

    No Known Activations