© 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. 100679
    Prev
    Next
    INDEX
    Explanations

    date structures

    np_acts-logits-general · gemini-2.5-flash-lite

    variable or property declarations related to dates or times in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    s
    -1.74
    ITATION
    -1.65
     durante
    -1.54
    zzleHttp
    -1.52
     desarroll
    -1.51
     ۷
    -1.49
    驁
    -1.48
    during
    -1.45
     mieten
    -1.41
     WHEN
    -1.41
    POSITIVE LOGITS
     time
    1.99
    我国
    1.50
    .
    1.40
     unparalleled
    1.38
     that
    1.34
    窣
    1.32
    🌸
    1.27
     because
    1.27
     Munic
    1.24
    Ruju
    1.21
    Activations Density 0.075%

    No Known Activations