© 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. 57470
    Prev
    Next
    INDEX
    Explanations

    Los Angeles Times

    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
    i
    -3.22
    '
    -3.17
    {
    -2.92
    t
    -2.53
    不管是
    -2.42
     來
    -2.41
    4
    -2.30
    不会
    -2.25
    ta
    -2.25
     It
    -2.17
    POSITIVE LOGITS
    </h6>
    2.61
    .
    2.55
     outras
    2.53
    媗
    2.53
     []
    2.48
     of
    2.41
    攫
    2.38
    鲽
    2.38
    痺
    2.36
     hauteur
    2.34
    Activations Density 0.004%

    No Known Activations