© 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. 22-GEMMASCOPE-RES-131K
    7. 66726
    Prev
    Next
    INDEX
    Explanations

    Western diet, Download somewhere, Q:

    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_22/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
     primarily
    -1.61
     mainly
    -1.59
     ALL
    -1.59
     several
    -1.55
     first
    -1.54
     all
    -1.52
     numerous
    -1.41
     both
    -1.41
     just
    -1.40
     September
    -1.38
    POSITIVE LOGITS
     startling
    1.42
     relâche
    1.30
     strikingly
    1.30
     :/
    1.29
     braço
    1.29
     insanely
    1.27
    ὴν
    1.27
     Dinas
    1.27
     gigantic
    1.26
     wondrous
    1.24
    Activations Density 0.000%

    No Known Activations