© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25841
    Prev
    Next
    INDEX
    Explanations

    LL, L.L.C., L.L.B., L.L. letters

    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
     sombrero
    -0.82
    澳門
    -0.81
     certaine
    -0.78
     dano
    -0.77
     dégustation
    -0.77
     cesta
    -0.75
     Agronomy
    -0.74
     Filtration
    -0.74
     comandante
    -0.74
     festa
    -0.73
    POSITIVE LOGITS
     LL
    1.45
    LL
    1.11
     ll
    1.08
    ll
    1.08
    oyd
    1.01
    ellyn
    1.00
    ellin
    0.93
     Lla
    0.91
     Cool
    0.90
     Ll
    0.89
    Activations Density 0.024%

    No Known Activations