© 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. 72720
    Prev
    Next
    INDEX
    Explanations

    transactional, transitional, symmetrical

    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
    s
    -3.08
     The
    -2.84
    t
    -2.34
    籥
    -2.34
     alcune
    -2.09
     spectacular
    -2.08
    僦
    -2.06
    ’
    -2.03
    蜮
    -1.99
     .......
    -1.95
    POSITIVE LOGITS
    𓆜
    2.31
    ～～
    2.27
    רושלים
    2.25
    啻
    2.08
    னர்
    2.08
    ？”
    2.05
     supremely
    2.02
    ordonnées
    2.00
    叔
    2.00
    しても
    1.99
    Activations Density 0.002%

    No Known Activations