© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    por, per, by, por example

    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
    も
    -0.92
    それも
    -0.91
    と
    -0.88
    もあって
    -0.86
    zący
    -0.82
    aking
    -0.82
     blessés
    -0.81
    それを
    -0.79
     Grenzen
    -0.79
    ซึ่ง
    -0.79
    POSITIVE LOGITS
     forfeit
    1.03
    default
    1.02
     virtue
    1.00
    menor
    0.99
     modesty
    0.92
     default
    0.91
     Sveriges
    0.90
     mistake
    0.90
     example
    0.88
    cina
    0.88
    Activations Density 0.004%

    No Known Activations