© 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. 33368
    Prev
    Next
    INDEX
    Explanations

    determiners followed by nouns

    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
     食事
    -1.25
    uyasha
    -1.19
     mété
    -1.16
     déplo
    -1.16
     recensement
    -1.12
     navire
    -1.11
    の良い
    -1.10
     brilla
    -1.10
    ute
    -1.09
    ificantly
    -1.09
    POSITIVE LOGITS
     nowadays
    1.37
     pretended
    1.35
     kind
    1.35
     freaking
    1.21
     mentioned
    1.21
     advises
    1.20
     notorious
    1.20
     adicional
    1.16
     cooperation
    1.14
     resulted
    1.09
    Activations Density 0.357%

    No Known Activations