© 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. 90546
    Prev
    Next
    INDEX
    Explanations

    food network shows and chefs

    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
     ESL
    -0.75
    tol
    -0.74
    ᠮ
    -0.73
     rotting
    -0.72
    ╪
    -0.71
     meurt
    -0.70
     الجد
    -0.70
    zepte
    -0.69
    lese
    -0.69
    ัก
    -0.69
    POSITIVE LOGITS
    Bare
    0.86
     Food
    0.85
     Iron
    0.81
     Rachael
    0.81
    network
    0.80
    Ree
    0.79
    scratch
    0.78
     Network
    0.77
     Bare
    0.76
     network
    0.75
    Activations Density 0.024%

    No Known Activations