© 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. 30542
    Prev
    Next
    INDEX
    Explanations

    license texts", "amazon", "windows"

    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
     насеља
    -0.83
    יס
    -0.69
     Structure
    -0.68
     quad
    -0.68
     legs
    -0.68
    AOC
    -0.67
     dört
    -0.66
    FileWriter
    -0.66
     structure
    -0.65
     remover
    -0.65
    POSITIVE LOGITS
     VM
    0.72
    Puede
    0.69
     सद
    0.68
    ).-
    0.68
     zorgen
    0.67
     tolua
    0.66
    quium
    0.66
     CMA
    0.66
    ostante
    0.64
     isset
    0.63
    Activations Density 0.058%

    No Known Activations