© 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. 68384
    Prev
    Next
    INDEX
    Explanations

    prepare for the next

    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
     either
    -0.85
     truncation
    -0.74
    这些
    -0.73
     here
    -0.71
     giornal
    -0.69
    Td
    -0.68
     vœ
    -0.68
     ours
    -0.68
    缚
    -0.68
    ३
    -0.68
    POSITIVE LOGITS
    vää
    0.88
     while
    0.87
     consultato
    0.82
    面向
    0.82
    另一种
    0.81
     terwijl
    0.79
     aller
    0.77
    』、
    0.77
    őd
    0.76
     nadat
    0.75
    Activations Density 0.150%

    No Known Activations