© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92962
    Prev
    Next
    INDEX
    Explanations

    space program figures

    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
    ynchron
    -0.74
    Predator
    -0.73
     поту
    -0.72
    omethane
    -0.70
     naselje
    -0.69
    観察
    -0.67
    Phylogenetic
    -0.67
    헌
    -0.66
     ورزشی
    -0.65
    asteroido
    -0.65
    POSITIVE LOGITS
    NASA
    1.70
     NASA
    1.66
     spacecraft
    1.48
     Space
    1.40
    Space
    1.28
     space
    1.26
     Huntsville
    1.24
    nasa
    1.23
     косми
    1.21
     Aerospace
    1.20
    Activations Density 0.058%

    No Known Activations