© 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. 34-GEMMASCOPE-RES-131K
    7. 87140
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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_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
     dolce
    -1.01
     clearColor
    -0.95
     pittores
    -0.95
     месяца
    -0.93
     Meksiko
    -0.91
    淅
    -0.90
     MINUTES
    -0.90
     komik
    -0.90
    leno
    -0.89
    ジャック
    -0.89
    POSITIVE LOGITS
     September
    1.12
     October
    1.07
     July
    1.04
     graders
    1.02
     August
    1.01
     gelukkig
    1.00
     June
    1.00
     February
    0.98
     edition
    0.98
     philanth
    0.96
    Activations Density 0.005%

    No Known Activations