© 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. 104523
    Prev
    Next
    INDEX
    Explanations

    code syntax closing elements

    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
    6
    -1.17
     these
    -1.10
     раз
    -1.05
    2
    -1.03
    8
    -1.02
     or
    -0.98
     such
    -0.96
    1
    -0.95
    9
    -0.94
     so
    -0.93
    POSITIVE LOGITS
    𝟭
    1.30
     febrero
    1.02
     държа
    1.01
     klock
    1.00
    𝟏
    1.00
    ₱
    0.94
    iség
    0.93
    ต้องการ
    0.93
    plz
    0.93
     тях
    0.92
    Activations Density 0.002%

    No Known Activations