© 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. 78025
    Prev
    Next
    INDEX
    Explanations

    Specific scientific and technical terms

    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
     яй
    -0.77
     eventName
    -0.76
    霧
    -0.74
     проек
    -0.74
     Industrial
    -0.73
     plug
    -0.71
     Valenzuela
    -0.71
    泊
    -0.71
     meman
    -0.70
     Omaha
    -0.69
    POSITIVE LOGITS
     Sre
    0.80
    影响
    0.77
    Pour
    0.77
    érée
    0.76
     simpl
    0.75
     특
    0.75
    Для
    0.74
     fd
    0.74
    tiert
    0.73
    asons
    0.72
    Activations Density 0.006%

    No Known Activations