© 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. 91271
    Prev
    Next
    INDEX
    Explanations

    apple framework imports

    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
     misconceptions
    -0.89
    綜
    -0.80
     hız
    -0.74
    zö
    -0.73
    攒
    -0.73
     bessere
    -0.72
    createdDate
    -0.71
     malpractice
    -0.71
     décès
    -0.70
    ldc
    -0.69
    POSITIVE LOGITS
    Foundation
    1.09
     Foundation
    1.08
     foundation
    0.88
    Core
    0.87
    foundation
    0.85
     Core
    0.82
    Kit
    0.79
    蠻
    0.79
     Hou
    0.75
    zehn
    0.73
    Activations Density 0.155%

    No Known Activations