© 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. 73537
    Prev
    Next
    INDEX
    Explanations

    October dates leading to Halloween

    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
     Thanksgiving
    -1.18
     August
    -1.05
     AUGUST
    -0.94
     September
    -0.92
    Thanksgiving
    -0.91
     鳳
    -0.90
    August
    -0.84
     Aug
    -0.84
     December
    -0.83
     Febru
    -0.80
    POSITIVE LOGITS
    🎃
    0.99
     Spo
    0.96
     Halloween
    0.87
    BOO
    0.82
     uniquement
    0.82
     trick
    0.82
    halloween
    0.81
    hallo
    0.81
    👻
    0.81
    spooky
    0.81
    Activations Density 0.062%

    No Known Activations