© 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. 48263
    Prev
    Next
    INDEX
    Explanations

    numbers and positive adverbs

    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
     homicidio
    -1.34
    Those
    -1.27
    ˃
    -1.21
     åp
    -1.18
     Although
    -1.18
    Even
    -1.16
     Those
    -1.15
    Jenis
    -1.14
     páginas
    -1.14
    These
    -1.14
    POSITIVE LOGITS
    0
    1.40
     strikingly
    1.31
     delightfully
    1.30
     immense
    1.27
     acclaimed
    1.27
     intriguing
    1.24
     amazingly
    1.23
     hugely
    1.23
     intrigu
    1.23
     remarkably
    1.22
    Activations Density 0.018%

    No Known Activations