© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104589
    Prev
    Next
    INDEX
    Explanations

    foreign characters and symbols

    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
     several
    -1.53
     before
    -1.52
     this
    -1.50
     countless
    -1.48
     Several
    -1.48
     many
    -1.46
     Although
    -1.44
     Numerous
    -1.44
     enhances
    -1.44
     numerous
    -1.42
    POSITIVE LOGITS
     vijf
    1.50
     delightfully
    1.48
     trois
    1.30
     insanely
    1.30
     unbelievably
    1.29
     strikingly
    1.29
     ridiculously
    1.29
     ib
    1.27
     quando
    1.25
     amazingly
    1.25
    Activations Density 0.004%

    No Known Activations