© 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. 22-GEMMASCOPE-RES-131K
    7. 33009
    Prev
    Next
    INDEX
    Explanations

    each, every, some in various languages

    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_22/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
     or
    -1.88
     during
    -1.57
     that
    -1.30
     which
    -1.29
    During
    -1.26
     знали
    -1.23
     on
    -1.23
     with
    -1.23
     so
    -1.21
     this
    -1.18
    POSITIVE LOGITS
     chacune
    1.45
     chacun
    1.27
     chaque
    1.22
     каждой
    1.20
     jeweils
    1.19
    subplot
    1.17
     atualizar
    1.12
     left
    1.11
     každé
    1.09
     alguns
    1.08
    Activations Density 0.031%

    No Known Activations