© 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. 10821
    Prev
    Next
    INDEX
    Explanations

    code execution or logic

    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
    眼里
    -0.90
    皺
    -0.89
    QUESTIONS
    -0.86
     wó
    -0.82
     násled
    -0.82
    otechnical
    -0.82
    šem
    -0.79
    hever
    -0.79
    体を
    -0.79
     demokra
    -0.79
    POSITIVE LOGITS
     again
    0.98
    日発売
    0.91
     extraordinarily
    0.90
    Again
    0.86
     вновь
    0.83
    今度は
    0.82
     године
    0.82
    {(-
    0.81
    例句
    0.81
     rupture
    0.80
    Activations Density 0.001%

    No Known Activations