© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1661
    Prev
    Next
    INDEX
    Explanations

    USC CFR sections and codes

    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
     角色
    -0.72
    cepat
    -0.67
     compress
    -0.67
     продукта
    -0.66
     органов
    -0.66
     نحوه
    -0.65
    ItemData
    -0.64
    瀵
    -0.63
     Weymouth
    -0.63
    tugas
    -0.62
    POSITIVE LOGITS
    PMC
    1.00
    SMC
    0.98
    pmc
    0.95
    适应
    0.89
     SMC
    0.87
    MMC
    0.81
     PMC
    0.81
    BMC
    0.79
    STC
    0.79
     Title
    0.78
    Activations Density 0.016%

    No Known Activations