© 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. 87023
    Prev
    Next
    INDEX
    Explanations

    onward(s) interspersed gamut Xamarin

    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
    {
    -2.59
    毉
    -2.52
    鹋
    -2.34
     condenado
    -2.33
     tomado
    -2.31
    それにしても
    -2.28
     sū
    -2.28
    𓆸
    -2.23
     centímetros
    -2.23
    <bos>
    -2.23
    POSITIVE LOGITS
    s
    3.78
    你
    3.02
    n
    2.92
    傒
    2.56
    ↵↵
    2.47
    不管是
    2.41
     You
    2.39
    та
    2.28
    ки
    2.27
    她
    2.27
    Activations Density 0.001%

    No Known Activations