© 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. 60774
    Prev
    Next
    INDEX
    Explanations

    groups acting together

    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
     himself
    -1.45
     kedua
    -1.20
    一人で
    -0.99
    Ȁ
    -0.98
     сам
    -0.97
     alone
    -0.95
    両
    -0.93
     kirjo
    -0.91
     eikä
    -0.91
     presiding
    -0.89
    POSITIVE LOGITS
     collectively
    2.19
     gathered
    1.88
     themselves
    1.80
     congreg
    1.77
     unanimously
    1.66
     each
    1.63
    全員
    1.57
     clustered
    1.53
     crowding
    1.50
     collective
    1.48
    Activations Density 0.059%

    No Known Activations