© 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. 91830
    Prev
    Next
    INDEX
    Explanations

    historical sites, names, and foreign words

    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
     DELIVER
    -0.79
     alami
    -0.76
    gså
    -0.75
     snowfall
    -0.73
    ۩
    -0.72
    mę
    -0.71
    []"
    -0.70
    为止
    -0.69
    Baba
    -0.69
     pronunci
    -0.69
    POSITIVE LOGITS
     empire
    0.75
    діть
    0.73
     inscription
    0.73
     board
    0.73
     चाल
    0.73
    cu
    0.72
    ud
    0.72
     insecticide
    0.71
     Anambra
    0.71
    alla
    0.70
    Activations Density 0.033%

    No Known Activations