© 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. 22-GEMMASCOPE-RES-131K
    7. 68576
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by verbs

    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
    敺
    -2.13
    がなく
    -2.06
    และ
    -2.02
     唯美
    -1.81
    鮰
    -1.76
    킁
    -1.74
     malé
    -1.74
     incrí
    -1.70
    tiéndose
    -1.69
     炖
    -1.68
    POSITIVE LOGITS
     taken
    1.90
     used
    1.88
     S
    1.59
     D
    1.55
    Although
    1.48
     R
    1.47
     G
    1.46
    ˗
    1.46
     by
    1.45
    S
    1.45
    Activations Density 0.110%

    No Known Activations