© 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. 22-GEMMASCOPE-RES-131K
    7. 14469
    Prev
    Next
    INDEX
    Explanations

    progression to the next item

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

    The neuron is keyed to the word “next,” activating strongly whenever that exact token appears.

    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
     LITER
    -1.84
     soooo
    -1.84
     BEAUT
    -1.79
     FRESH
    -1.77
     sooo
    -1.77
    なかな
    -1.76
     GETTING
    -1.74
    providing
    -1.74
    inerario
    -1.73
    还挺
    -1.73
    POSITIVE LOGITS
     one
    2.36
     two
    2.14
     thing
    2.06
     three
    1.96
     Each
    1.83
     five
    1.68
     time
    1.67
    </u>
    1.65
     Every
    1.61
     eight
    1.57
    Activations Density 0.020%

    No Known Activations