© 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. 67458
    Prev
    Next
    INDEX
    Explanations

    concepts of afterlife and damnation

    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
    檮
    -1.79
     图库
    -1.73
    鐃
    -1.67
    ︕
    -1.50
     »,
    -1.50
    橦
    -1.47
    犼
    -1.46
     sello
    -1.45
    もしれません
    -1.45
     huu
    -1.45
    POSITIVE LOGITS
    (
    1.27
    "
    1.27
     more
    1.27
     better
    1.26
     even
    1.22
     вместо
    1.21
     R
    1.20
     lack
    1.20
     where
    1.18
     consider
    1.18
    Activations Density 0.017%

    No Known Activations