© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59416
    Prev
    Next
    INDEX
    Explanations

    date and time formatting

    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
     people
    -0.84
    与此同时
    -0.83
    その
    -0.82
     aplica
    -0.80
    ínu
    -0.76
     Aplica
    -0.75
    typeId
    -0.74
    Vaata
    -0.74
     озе
    -0.74
     jobs
    -0.73
    POSITIVE LOGITS
    yyyy
    1.05
    YYYY
    0.94
    nál
    0.87
     decrypt
    0.87
    lowers
    0.86
     DATE
    0.85
     January
    0.85
     Māori
    0.84
     esterna
    0.81
    ământ
    0.81
    Activations Density 0.015%

    No Known Activations