© 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. 84046
    Prev
    Next
    INDEX
    Explanations

    box-sizing

    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
     with
    -1.52
    どうなる
    -1.47
     große
    -1.39
    ’，
    -1.37
     does
    -1.37
    المشار
    -1.37
    ！！！”
    -1.35
     and
    -1.34
    贷款
    -1.33
     considerable
    -1.32
    POSITIVE LOGITS
    return
    1.80
    跸
    1.55
    必须要
    1.52
     derniers
    1.51
    culoskeletal
    1.45
    basically
    1.45
    completely
    1.40
    being
    1.40
     rechte
    1.40
     nemico
    1.39
    Activations Density 0.088%

    No Known Activations