© 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. 84814
    Prev
    Next
    INDEX
    Explanations

    become or experience change

    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
    եկ
    -1.00
     occupies
    -0.98
     occupy
    -0.97
     occupying
    -0.93
     resides
    -0.92
    wira
    -0.91
     inhabiting
    -0.89
    亹
    -0.87
     strolling
    -0.85
    álja
    -0.84
    POSITIVE LOGITS
     become
    1.55
     witness
    1.52
     menjadi
    1.39
     becoming
    1.35
     witnessed
    1.32
     receive
    1.28
     receives
    1.28
     witnessing
    1.27
     becomes
    1.26
     experiencing
    1.24
    Activations Density 0.087%

    No Known Activations