© 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. 117777
    Prev
    Next
    INDEX
    Explanations

    new age spirituality and metaphysics

    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
     deportivo
    -0.84
    ボーナス
    -0.81
    ปิด
    -0.79
    PlainText
    -0.77
    rosophila
    -0.73
    awtextra
    -0.71
     Compañía
    -0.71
    mAdapter
    -0.71
     useDispatch
    -0.70
     medios
    -0.70
    POSITIVE LOGITS
     New
    2.11
    New
    1.86
     spiritual
    1.62
     spirituality
    1.57
     Spiritual
    1.34
    spiritual
    1.32
     espiritual
    1.26
     Reiki
    1.19
    スピ
    1.17
    Spiritual
    1.14
    Activations Density 0.030%

    No Known Activations