© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112523
    Prev
    Next
    INDEX
    Explanations

    blinking

    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
     you
    -2.59
    屨
    -2.44
     (‘
    -2.42
    秝
    -2.42
    卺
    -2.39
    ޓ
    -2.36
     tidak
    -2.34
    蓠
    -2.31
    咈
    -2.28
    ですが
    -2.27
    POSITIVE LOGITS
    “
    3.14
     '
    2.89
    y
    2.61
    `
    2.44
    ",
    2.36
    -
    2.31
    {
    2.25
    可以
    2.25
    ations
    2.20
    ate
    2.16
    Activations Density 0.001%

    No Known Activations