© 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. 34-GEMMASCOPE-RES-131K
    7. 99020
    Prev
    Next
    INDEX
    Explanations

    seasonal periods

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

    The neuron fires strongly on season names (e.g. autumn, spring, summer, fall) when they appear as part of date or time references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    droje
    -0.92
    マフラー
    -0.85
    Scrollbar
    -0.85
    プラスチック
    -0.85
    ılığı
    -0.84
     zmien
    -0.84
    なかな
    -0.83
     проектов
    -0.83
    がたくさん
    -0.82
    昔から
    -0.82
    POSITIVE LOGITS
     semester
    1.50
    🍂
    1.06
    semester
    1.05
     equinox
    1.04
     season
    0.99
    🌷
    0.94
    Semester
    0.92
    🍁
    0.92
     semestre
    0.91
     when
    0.88
    Activations Density 0.017%

    No Known Activations