© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85141
    Prev
    Next
    INDEX
    Explanations

    "one" followed by a verb

    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
     you
    -1.73
     каждого
    -1.72
     our
    -1.57
     each
    -1.55
     are
    -1.47
     we
    -1.32
     he
    -1.28
     imma
    -1.23
    us
    -1.20
     каждый
    -1.16
    POSITIVE LOGITS
     oneself
    1.77
    СТИ
    1.45
    ঋ
    1.36
     intenciones
    1.34
     mentiras
    1.32
     ioutil
    1.31
    bujete
    1.29
    Ꮀ
    1.29
    bellar
    1.29
    čit
    1.29
    Activations Density 0.033%

    No Known Activations