© 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. 31575
    Prev
    Next
    INDEX
    Explanations

    words starting with L or Li/La

    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
    feeder
    -0.80
     feeder
    -0.77
     HY
    -0.73
     Result
    -0.71
     Imp
    -0.70
    分散
    -0.69
    椰
    -0.67
     CM
    -0.65
     CL
    -0.65
     Report
    -0.64
    POSITIVE LOGITS
    Peru
    0.92
     peru
    0.86
     Shawnee
    0.85
     Colbert
    0.84
     Peru
    0.81
    aratus
    0.75
     affari
    0.74
     Cowell
    0.74
     SoC
    0.73
     Allentown
    0.73
    Activations Density 0.053%

    No Known Activations