© 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. 98279
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliary 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
     konkrete
    -1.11
    🤏
    -1.10
    neat
    -1.05
    continues
    -1.05
     tle
    -1.02
     bemerk
    -1.02
     choisir
    -1.01
    riy
    -0.99
    Ecole
    -0.98
    本來
    -0.97
    POSITIVE LOGITS
     here
    1.59
     this
    1.51
     only
    1.50
     there
    1.44
     while
    1.38
     as
    1.30
     too
    1.23
     although
    1.17
     despite
    1.16
     these
    1.15
    Activations Density 0.043%

    No Known Activations