© 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. 56039
    Prev
    Next
    INDEX
    Explanations

    transitional justice question citations

    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
    言语
    -0.79
    forestation
    -0.75
    verbosity
    -0.74
     מס
    -0.72
     academics
    -0.71
     Timing
    -0.70
     verle
    -0.70
     berangkat
    -0.70
     thyself
    -0.67
    pta
    -0.67
    POSITIVE LOGITS
    ueuse
    0.85
    𝔯
    0.80
    scores
    0.80
    owicz
    0.80
    DDT
    0.80
    tuje
    0.79
    Hundreds
    0.77
    ueux
    0.75
    憨
    0.75
    Mosaic
    0.74
    Activations Density 0.004%

    No Known Activations