© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98968
    Prev
    Next
    INDEX
    Explanations

    events and actions

    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
     emojis
    -1.79
     covid
    -1.78
    https
    -1.77
    nullptr
    -1.72
     https
    -1.68
     emoji
    -1.67
    令和
    -1.58
     selfies
    -1.57
     microbiome
    -1.55
    covid
    -1.48
    POSITIVE LOGITS
     idéia
    1.53
     "[
    1.35
     Arxivat
    1.32
     eight
    1.28
    myspace
    1.28
     According
    1.27
    “[
    1.26
    "[
    1.24
     “[
    1.22
    According
    1.21
    Activations Density 0.259%

    No Known Activations