© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66552
    Prev
    Next
    INDEX
    Explanations

    vectors and operators

    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
     by
    -2.77
     superbly
    -2.25
     when
    -2.25
     during
    -2.20
     because
    -2.20
    During
    -2.17
    Not
    -2.17
     epitom
    -2.11
     exquisite
    -2.03
     at
    -2.02
    POSITIVE LOGITS
    奩
    2.25
    ᠋
    2.23
    ఽ
    2.23
    enablog
    2.19
    哙
    2.17
     trám
    2.14
     semelh
    2.03
     Provides
    2.02
    鹩
    2.00
    튿
    1.99
    Activations Density 0.001%

    No Known Activations