© 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. 64051
    Prev
    Next
    INDEX
    Explanations

    "Big" followed by a capitalized word

    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
     especí
    -0.85
    ↵↵
    -0.79
     Hø
    -0.76
     peeking
    -0.75
     Primeiro
    -0.73
    menos
    -0.71
    abril
    -0.71
     aeroporto
    -0.70
    Llama
    -0.70
    ESSMENT
    -0.70
    POSITIVE LOGITS
    Big
    1.55
     Big
    1.50
    foot
    1.38
    big
    1.27
    gers
    1.13
    oted
    1.11
    gie
    1.11
    geset
    1.05
    gins
    1.03
     BIG
    1.01
    Activations Density 0.014%

    No Known Activations