© 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. 84122
    Prev
    Next
    INDEX
    Explanations

    referencing the past

    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
    later
    -1.05
     later
    -1.04
     Later
    -1.01
     Subsequent
    -0.97
     subsequent
    -0.93
     eventual
    -0.92
     später
    -0.88
     بعدی
    -0.84
     LATER
    -0.81
    Later
    -0.80
    POSITIVE LOGITS
     past
    4.13
     Vergangenheit
    2.88
    過去
    2.77
    past
    2.61
     прошлом
    2.55
     прошлого
    2.47
     passato
    2.44
     przesz
    2.42
    过去
    2.39
    Past
    2.38
    Activations Density 0.051%

    No Known Activations