© 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. 7554
    Prev
    Next
    INDEX
    Explanations

    appearance, reflection, creation, Christ

    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
    NESS
    -1.35
    🢒
    -1.28
    чя
    -1.27
    the
    -1.25
    。「
    -1.24
    \">
    -1.19
    matchCondition
    -1.18
    mouseleave
    -1.18
    navigationBar
    -1.18
     JpaRepository
    -1.14
    POSITIVE LOGITS
     therefore
    1.26
     still
    1.22
    Вывод
    1.10
     falda
    1.08
     vissa
    1.07
    Juegos
    1.07
    نور
    1.06
     tunik
    1.03
    </h2>
    1.02
     ilang
    1.02
    Activations Density 0.029%

    No Known Activations