© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    place names and foreign currencies

    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
    ↵
    -3.30
     mammoth
    -2.70
    た
    -2.47
     multitude
    -2.41
     resolute
    -2.38
     flimsy
    -2.33
     blistering
    -2.31
    慙
    -2.31
     instalar
    -2.28
    èrement
    -2.22
    POSITIVE LOGITS
    ზ
    2.78
    苼
    2.33
    螃
    2.30
    耵
    2.28
    viously
    2.23
    ጐ
    2.23
    觏
    2.20
    唻
    2.20
    鈊
    2.19
    ."
    2.11
    Activations Density 0.001%

    No Known Activations