© 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. 13009
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

    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
    -1.27
     Milán
    -1.14
    <>
    -1.09
     instead
    -1.09
     везе
    -1.07
    мл
    -1.05
    ᵉ
    -1.05
     farmhouse
    -1.05
     март
    -1.05
    😜
    -1.04
    POSITIVE LOGITS
    ͮ
    1.15
    endroit
    1.09
    ⅈ
    1.07
    ńskim
    1.04
    Spesifikasi
    1.04
    ͧ
    1.02
    ͩ
    1.00
    紹介します
    1.00
     dergleichen
    0.99
    Hechos
    0.99
    Activations Density 0.025%

    No Known Activations