© 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. 70541
    Prev
    Next
    INDEX
    Explanations

    "ref" tags and citations

    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
     fré
    -1.00
     hydrauli
    -0.96
     ananas
    -0.96
     chers
    -0.94
     rouges
    -0.94
     espagnol
    -0.93
     milj
    -0.91
     surpl
    -0.90
     vatt
    -0.90
    ⸪
    -0.90
    POSITIVE LOGITS
    iapkan
    0.94
    phère
    0.93
    וּ
    0.88
     \\
    0.88
    lında
    0.88
     используя
    0.87
     \_
    0.85
    ycznie
    0.84
     ")
    0.84
     ``
    0.84
    Activations Density 0.059%

    No Known Activations