© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20204
    Prev
    Next
    INDEX
    Explanations

    legal cases or state matters

    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
     ...
    -1.57
    これに
    -1.36
    fillment
    -1.34
    })()
    -1.34
     hafta
    -1.32
    今度は
    -1.28
    queryInterface
    -1.28
     our
    -1.27
    >`
    -1.27
     necessari
    -1.27
    POSITIVE LOGITS
    edakan
    1.52
    età
    1.52
     clothes
    1.51
     offenbar
    1.47
     Aufmerksamkeit
    1.44
     мужская
    1.43
    anhänger
    1.41
     California
    1.41
     държа
    1.40
     Gegensatz
    1.38
    Activations Density 0.001%

    No Known Activations