© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4034
    Prev
    Next
    INDEX
    Explanations

    included or attached content

    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
    vollen
    -0.81
    íp
    -0.77
    Viewed
    -0.74
     ospiti
    -0.73
    ība
    -0.73
     Taras
    -0.72
     introducido
    -0.72
    샛
    -0.71
     Нам
    -0.70
    ndata
    -0.70
    POSITIVE LOGITS
     included
    4.28
     include
    3.84
     attached
    3.44
     attach
    3.28
     attaching
    3.14
    included
    3.13
     Include
    3.13
     Included
    2.98
    attach
    2.97
    Include
    2.92
    Activations Density 0.133%

    No Known Activations