© 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. 34-GEMMASCOPE-RES-131K
    7. 98141
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and articles

    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_34/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
     Hijo
    -1.29
     brille
    -1.24
     Ukraina
    -1.23
     Meksiko
    -1.22
     Januari
    -1.21
     ingat
    -1.20
     geene
    -1.16
     saati
    -1.16
    Thankfully
    -1.15
     harap
    -1.13
    POSITIVE LOGITS
     characteristics
    1.32
     necessary
    1.23
     so
    1.21
     also
    1.20
     analyzes
    1.18
     already
    1.17
     responsible
    1.15
     participation
    1.15
     indicated
    1.15
     intervened
    1.14
    Activations Density 0.067%

    No Known Activations