© 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. 10-GEMMASCOPE-RES-131K
    4. 131038
    Prev
    Next
    INDEX
    Explanations

    sequence and alternatives

    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_10/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
     it
    -2.47
     at
    -2.41
     their
    -2.34
     its
    -2.11
     in
    -2.06
     by
    -2.00
     during
    -1.88
     all
    -1.86
     there
    -1.84
     which
    -1.84
    POSITIVE LOGITS
    ᐈ
    2.00
     चुनें
    1.84
     then
    1.84
     téléph
    1.84
     тогда
    1.73
     kemudian
    1.73
     якщо
    1.69
    ardı
    1.67
    Then
    1.63
    然后
    1.63
    Activations Density 0.147%

    No Known Activations