© 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. 130579
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ing

    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
     have
    -2.11
    ！】
    -1.70
     still
    -1.66
     can
    -1.63
     cannot
    -1.55
     use
    -1.52
    Although
    -1.48
     same
    -1.48
    Despite
    -1.47
    They
    -1.46
    POSITIVE LOGITS
     テープ
    1.71
    freundlich
    1.58
     elegantly
    1.55
    鼉
    1.55
    onlu
    1.55
    posible
    1.55
    ほんと
    1.52
    箧
    1.51
    mycompany
    1.48
     واتس
    1.47
    Activations Density 0.072%

    No Known Activations