© 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. 81558
    Prev
    Next
    INDEX
    Explanations

    female pronoun 'her'

    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
     ziyaretçi
    -1.28
    搂
    -1.25
    itmen
    -1.20
    ellige
    -1.20
    耦
    -1.19
    Geograf
    -1.14
    celotti
    -1.14
     Rptr
    -1.14
     diesem
    -1.11
    nés
    -1.10
    POSITIVE LOGITS
     herself
    1.95
     own
    1.73
     daughter
    1.50
     husband
    1.34
    self
    1.27
    她
    1.27
    herself
    1.26
     in
    1.22
     sister
    1.20
     parents
    1.16
    Activations Density 0.012%

    No Known Activations