© 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. 58915
    Prev
    Next
    INDEX
    Explanations

    academic year or season

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

    The neuron detects numeric year tokens and date references (e.g. “2011–2012,” “2009–2010,” etc.).

    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
     and
    -1.62
     is
    -1.34
     欣赏
    -1.34
     different
    -1.34
    人と
    -1.29
    \
    -1.28
    tichetta
    -1.23
     many
    -1.23
     có
    -1.20
     لذا
    -1.17
    POSITIVE LOGITS
    فقط
    1.48
     vuotta
    1.45
     yeme
    1.45
    موقع
    1.44
    bánh
    1.39
    juries
    1.38
    besos
    1.36
    dibujos
    1.36
     menghar
    1.36
     blessures
    1.33
    Activations Density 0.039%

    No Known Activations