© 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. 90676
    Prev
    Next
    INDEX
    Explanations

    names starting with jan

    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
    ynie
    -0.83
     octavo
    -0.83
    ástico
    -0.83
    ERALD
    -0.81
    芸術
    -0.77
    vimento
    -0.75
     Terrain
    -0.74
    listItem
    -0.73
     Grands
    -0.72
    asString
    -0.72
    POSITIVE LOGITS
     Jan
    1.16
    Jan
    1.14
    January
    1.07
     يناير
    1.04
     jan
    0.94
    itors
    0.93
     January
    0.91
    usz
    0.91
     periodic
    0.88
    january
    0.88
    Activations Density 0.029%

    No Known Activations