© 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. 71505
    Prev
    Next
    INDEX
    Explanations

    qualifying adverbs and emphasis

    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
     eſt
    -1.32
    Câ
    -1.17
     curar
    -1.16
     userList
    -1.16
     sympa
    -1.15
     teto
    -1.14
     altera
    -1.14
     algodón
    -1.14
    Belarus
    -1.14
     dette
    -1.13
    POSITIVE LOGITS
     vielleicht
    1.50
     It
    1.40
     maybe
    1.36
     powiedzieć
    1.36
    ที่จะ
    1.35
     I
    1.33
     you
    1.30
     kanske
    1.28
    It
    1.20
    、
    1.16
    Activations Density 0.012%

    No Known Activations