© 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. 59078
    Prev
    Next
    INDEX
    Explanations

    sample or mock data initialization

    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
    였
    -0.80
     herum
    -0.75
    Dios
    -0.73
    entrion
    -0.72
     cantando
    -0.72
     гле
    -0.71
     BrowserModule
    -0.69
     formé
    -0.68
     elles
    -0.68
    ꧁
    -0.68
    POSITIVE LOGITS
     mock
    2.56
    mock
    2.44
     dummy
    2.38
     Mock
    2.14
     sample
    2.14
    Mock
    2.11
    dummy
    2.09
     fake
    2.03
    Dummy
    1.94
    MOCK
    1.83
    Activations Density 0.063%

    No Known Activations