© 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. 92210
    Prev
    Next
    INDEX
    Explanations

    SNAP, food, WIC

    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
     Aes
    -0.83
    startX
    -0.82
     peppermint
    -0.73
    真理
    -0.72
    Fries
    -0.72
     Neem
    -0.69
     oregano
    -0.69
     popo
    -0.69
     royalties
    -0.68
     chaise
    -0.68
    POSITIVE LOGITS
     SNAP
    1.74
    SNAP
    1.54
     food
    1.51
     Food
    1.30
     Snap
    1.20
    Food
    1.18
    food
    1.16
     foods
    1.16
     WIC
    1.12
     Nutrition
    1.09
    Activations Density 0.012%

    No Known Activations