© 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. 119144
    Prev
    Next
    INDEX
    Explanations

    family in-law

    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
    Invent
    -0.84
    买了
    -0.81
    带上
    -0.80
    metri
    -0.77
    alties
    -0.76
    buses
    -0.75
    bills
    -0.74
     φο
    -0.74
    太多了
    -0.74
    isierung
    -0.73
    POSITIVE LOGITS
    in
    1.39
     in
    1.13
    In
    1.05
    IN
    0.95
     In
    0.95
     IN
    0.85
     bandou
    0.84
     law
    0.79
    -
    0.79
    イン
    0.79
    Activations Density 0.014%

    No Known Activations