© 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. 34-GEMMASCOPE-RES-131K
    7. 7288
    Prev
    Next
    INDEX
    Explanations

    vessel names and prefixes

    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_34/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
     merkezi
    -0.87
    就直接
    -0.83
     butler
    -0.79
     alanı
    -0.78
     rite
    -0.78
    不清楚
    -0.77
     Bahnhof
    -0.77
    anar
    -0.77
     Posteriormente
    -0.76
     odası
    -0.75
    POSITIVE LOGITS
     USS
    1.20
     HMS
    0.87
    USS
    0.87
    CSS
    0.84
     Resolution
    0.82
     sleek
    0.80
     Lady
    0.77
    ŝ
    0.77
    <em>
    0.75
     capelli
    0.74
    Activations Density 0.054%

    No Known Activations