© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39781
    Prev
    Next
    INDEX
    Explanations

    months, days, and seasons

    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_22/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
    från
    -1.08
    などが
    -1.06
     fiebre
    -1.05
    gebühren
    -1.04
     mencionó
    -1.03
     máme
    -1.03
    parece
    -1.03
    ݯ
    -1.02
     dì
    -1.02
    ická
    -1.02
    POSITIVE LOGITS
     What
    1.17
     or
    1.07
     After
    1.05
     pre
    1.04
     Before
    0.98
     before
    0.98
     offseason
    0.94
     re
    0.93
     damage
    0.92
    時点
    0.92
    Activations Density 0.028%

    No Known Activations