© 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. 80981
    Prev
    Next
    INDEX
    Explanations

    what happens when or if asked

    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
     sokak
    -1.03
     pourquoi
    -0.95
     something
    -0.93
     acogedor
    -0.92
     conçus
    -0.89
     hoạch
    -0.87
     pazar
    -0.87
     grano
    -0.86
    何故
    -0.86
    Again
    -0.85
    POSITIVE LOGITS
     after
    1.88
     when
    1.67
     next
    1.65
     if
    1.45
     to
    1.41
     дальше
    1.41
     first
    1.30
     now
    1.29
     with
    1.27
     afterwards
    1.23
    Activations Density 0.032%

    No Known Activations