© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74448
    Prev
    Next
    INDEX
    Explanations

    HTML select elements

    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
     depois
    -1.78
    Its
    -1.76
     \{
    -1.67
    吃了
    -1.50
     -.
    -1.45
     a
    -1.44
     '
    -1.43
    了一
    -1.41
    它的
    -1.41
     Its
    -1.40
    POSITIVE LOGITS
    ,”
    1.73
    ghalaya
    1.52
     through
    1.46
     開催
    1.46
     from
    1.43
    เปลี่ยน
    1.38
    んだよね
    1.34
     including
    1.34
    هایت
    1.30
    estries
    1.30
    Activations Density 0.006%

    No Known Activations