© 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. 10-GEMMASCOPE-RES-131K
    7. 9630
    Prev
    Next
    INDEX
    Explanations

    defining extension methods with `this`

    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_10/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
     are
    -1.55
     will
    -1.55
    氿
    -1.51
     
    -1.50
    <bos>
    -1.44
    </h3>
    -1.39
     MUCH
    -1.35
    来到了
    -1.35
     kurzem
    -1.34
    なんとなく
    -1.33
    POSITIVE LOGITS
     the
    2.00
     in
    1.69
    ية
    1.55
    tional
    1.55
    ementara
    1.52
    wa
    1.48
    iric
    1.48
    y
    1.46
    ga
    1.42
    ícias
    1.40
    Activations Density 0.007%

    No Known Activations