© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64612
    Prev
    Next
    INDEX
    Explanations

    Lancaster, Pennsylvania

    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
     Talla
    -0.80
    渤
    -0.78
    ']);
    -0.77
     Situations
    -0.76
    proc
    -0.73
     beagle
    -0.72
     Ceramics
    -0.72
    స
    -0.70
    lean
    -0.69
     Algo
    -0.69
    POSITIVE LOGITS
     Lancaster
    1.35
    Lancaster
    1.23
     Stras
    0.83
     Amish
    0.80
     svet
    0.79
     LAN
    0.72
     nostri
    0.69
     pól
    0.69
     Жа
    0.68
     Furman
    0.68
    Activations Density 0.036%

    No Known Activations