© 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. 116429
    Prev
    Next
    INDEX
    Explanations

    organizing and managing events

    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
    ised
    -1.20
    th
    -1.19
    does
    -1.18
    almost
    -1.13
    eight
    -1.12
    known
    -1.12
    再一次
    -1.12
    瘣
    -1.10
     renowned
    -1.10
     uncovering
    -1.09
    POSITIVE LOGITS
    uality
    1.86
    brite
    1.55
     planner
    1.37
     suced
    1.28
     evento
    1.24
     event
    1.23
    ！！！！
    1.21
     måneder
    1.21
     Events
    1.20
     planners
    1.18
    Activations Density 0.028%

    No Known Activations