© 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. 10-GEMMASCOPE-RES-131K
    7. 86866
    Prev
    Next
    INDEX
    Explanations

    Hyundai and Tay

    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_10/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
    2
    -4.00
    0
    -3.64
    1
    -3.44
    3
    -3.25
    9
    -3.06
    7
    -3.06
    6
    -3.00
    5
    -3.00
     “
    -2.89
    8
    -2.86
    POSITIVE LOGITS
    嬗
    3.31
    讴
    3.08
    膂
    3.03
     馆
    2.59
    白衣
    2.58
    戕
    2.52
     暗
    2.50
    統領
    2.48
    岿
    2.47
    釓
    2.39
    Activations Density 0.001%

    No Known Activations