© 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. 68005
    Prev
    Next
    INDEX
    Explanations

    technical documentation and ratings

    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
     it
    -1.76
     them
    -1.75
     even
    -1.42
     its
    -1.39
     those
    -1.33
     then
    -1.28
     his
    -1.27
    それを
    -1.27
    </h2>
    -1.24
     got
    -1.23
    POSITIVE LOGITS
     misalnya
    1.36
    無論
    1.31
    是啊
    1.26
    鐽
    1.24
     tiefe
    1.24
    роки
    1.23
     moody
    1.23
     Außer
    1.22
    alumno
    1.21
     brightening
    1.20
    Activations Density 0.001%

    No Known Activations