© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19368
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     of
    -2.00
     and
    -1.87
     on
    -1.63
     every
    -1.41
     at
    -1.39
     in
    -1.35
     på
    -1.33
     during
    -1.24
     from
    -1.23
     no
    -1.20
    POSITIVE LOGITS
    iações
    1.34
     sels
    1.34
     プル
    1.30
     chariots
    1.30
     pensare
    1.30
     impieg
    1.29
     utilizz
    1.27
     pite
    1.27
     spiega
    1.27
     parlare
    1.27
    Activations Density 0.110%

    No Known Activations