© 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. 98572
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns like this and these

    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
     ativar
    -1.19
     tergantung
    -1.14
     keines
    -1.13
     ПРИ
    -1.12
     livré
    -1.10
     Cantidad
    -1.08
     seven
    -1.08
     seleccionamos
    -1.06
     reichlich
    -1.05
    Today
    -1.05
    POSITIVE LOGITS
     this
    2.72
     این
    1.79
    この
    1.66
     these
    1.59
     such
    1.51
    這個
    1.51
     dieser
    1.50
    这项
    1.50
     denna
    1.45
    此
    1.44
    Activations Density 0.084%

    No Known Activations