© 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. 34-GEMMASCOPE-RES-131K
    7. 91236
    Prev
    Next
    INDEX
    Explanations

    soul and related words

    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
     Norvège
    -0.83
    ENTIALS
    -0.74
    igable
    -0.73
     schä
    -0.72
    èce
    -0.72
     preocupación
    -0.72
    真實
    -0.72
    ضاف
    -0.71
     butt
    -0.71
     safeguard
    -0.70
    POSITIVE LOGITS
    sou
    1.21
     SOUL
    1.20
     Soul
    1.20
    Soul
    1.17
     soul
    1.04
    soul
    1.01
     gebildet
    0.90
     Souls
    0.89
    🧐
    0.84
     souls
    0.83
    Activations Density 0.008%

    No Known Activations