© 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. 41572
    Prev
    Next
    INDEX
    Explanations

    verbs of action and change

    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
     voordat
    -1.17
     każdy
    -1.08
     gemens
    -1.07
    みんな
    -1.06
    這些
    -1.05
    这样的
    -1.05
    同
    -1.04
    这些
    -1.03
    要么
    -1.03
    ाह
    -0.99
    POSITIVE LOGITS
     better
    1.45
     more
    1.40
     in
    1.38
     also
    1.36
     less
    1.27
     thereby
    1.14
     so
    1.13
    人也
    1.10
     by
    1.07
     further
    1.07
    Activations Density 0.228%

    No Known Activations