© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34261
    Prev
    Next
    INDEX
    Explanations

    subsequent events

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is detecting sentence boundaries—especially the words and punctuation that occur at the ends (and beginnings) of sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ALLEL
    -0.97
     tegas
    -0.94
     kado
    -0.90
     Backman
    -0.88
     katk
    -0.87
     kanal
    -0.83
     maja
    -0.80
    举动
    -0.80
     teks
    -0.79
    untos
    -0.78
    POSITIVE LOGITS
     later
    3.36
     subsequently
    2.64
    后来
    2.58
    later
    2.42
    Later
    2.25
     subsequent
    2.16
     Later
    2.16
     später
    2.13
    その後
    2.05
    後來
    2.02
    Activations Density 0.100%

    No Known Activations