© 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. 93155
    Prev
    Next
    INDEX
    Explanations

    possessive adjectives and determiners

    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
    甭
    -1.35
     captiv
    -1.27
     discer
    -1.26
     бампер
    -1.25
     réalisateur
    -1.23
    ƙ
    -1.23
     Brésil
    -1.21
     Projektu
    -1.20
     indien
    -1.20
     naï
    -1.19
    POSITIVE LOGITS
     these
    1.77
     this
    1.73
     information
    1.63
     things
    1.61
     services
    1.51
     activities
    1.48
     doing
    1.38
     funds
    1.38
     actions
    1.35
     analysis
    1.33
    Activations Density 0.047%

    No Known Activations