© 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. 70775
    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
    PENDAHULUAN
    -1.91
    鱨
    -1.76
     puissent
    -1.72
     journaliste
    -1.71
     efekty
    -1.70
     melap
    -1.69
     lã
    -1.66
     consé
    -1.65
    蠵
    -1.64
    Seni
    -1.61
    POSITIVE LOGITS
     has
    2.38
    A
    2.27
    R
    2.19
     are
    2.19
    '
    2.17
    M
    2.14
    is
    2.03
    H
    2.02
    "
    2.02
    d
    2.00
    Activations Density 0.089%

    No Known Activations