© 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. 10-GEMMASCOPE-RES-131K
    7. 129177
    Prev
    Next
    INDEX
    Explanations

    evacuating or seeking shelter

    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
     Even
    -1.38
     that
    -1.35
     troubling
    -1.28
     dazzling
    -1.25
     EVERY
    -1.21
     perplexing
    -1.20
     HUGE
    -1.20
     poignant
    -1.18
    šní
    -1.17
    робнее
    -1.16
    POSITIVE LOGITS
     instead
    1.31
    有個
    1.17
    熥
    1.13
    deemed
    1.12
    一邊
    1.12
    LAH
    1.11
    
    1.10
     trem
    1.09
    repeated
    1.09
    ではなく
    1.09
    Activations Density 0.038%

    No Known Activations