© 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. 60056
    Prev
    Next
    INDEX
    Explanations

    was/is followed by article or pronoun

    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
     écla
    -1.23
     épar
    -1.22
     refroid
    -1.21
    rictive
    -1.18
     antaranya
    -1.17
    rafted
    -1.16
     éte
    -1.15
     minimalista
    -1.14
     sommes
    -1.12
    ducción
    -1.11
    POSITIVE LOGITS
     through
    3.23
     from
    2.81
     because
    2.78
     in
    2.64
     this
    2.52
     during
    2.41
     when
    2.34
     with
    2.28
     only
    2.20
     after
    2.05
    Activations Density 0.023%

    No Known Activations