© 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. 129576
    Prev
    Next
    INDEX
    Explanations

    java.time.LocalDate

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

    The neuron identifies occurrences of the Java class name “LocalDate” (e.g. in import statements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    肫
    -2.56
    翃
    -2.53
    尨
    -2.48
    玏
    -2.36
    AdvEx
    -2.36
    la
    -2.34
    iconos
    -2.33
    indeer
    -2.31
    婼
    -2.28
    ⃢
    -2.28
    POSITIVE LOGITS
    6
    2.55
    ви
    2.42
    8
    2.41
    Если
    2.22
    ……」
    2.22
    because
    2.20
    를
    2.20
    ра
    2.20
                
    2.20
    2.17
    Activations Density 0.007%
    No Known Activations