© 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. 9447
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by punctuation

    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
     certaines
    -1.00
     certain
    -0.98
     everything
    -0.96
    randi
    -0.90
     PIL
    -0.90
    shelter
    -0.89
    kalk
    -0.87
    apropri
    -0.86
    hijab
    -0.86
     fire
    -0.85
    POSITIVE LOGITS
    FONTE
    1.00
    靥
    0.91
     berserk
    0.90
    wendung
    0.90
     delinquent
    0.89
    Автор
    0.88
    dası
    0.88
    ža
    0.87
     eser
    0.86
    Hvis
    0.86
    Activations Density 0.006%

    No Known Activations