© 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. 22-GEMMASCOPE-RES-131K
    7. 28445
    Prev
    Next
    INDEX
    Explanations

    either or

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

    The neuron fires strongly on occurrences of the word “until,” i.e. loop‐termination or repetition‐until phrasing.

    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
     チ
    -0.91
     мамы
    -0.91
     manner
    -0.91
    alp
    -0.90
     ně
    -0.89
    :^{
    -0.88
    |$.
    -0.87
    を整
    -0.85
    dalam
    -0.85
     PLAY
    -0.85
    POSITIVE LOGITS
     either
    2.97
     or
    2.59
     либо
    2.58
    either
    2.55
    Either
    2.36
     Either
    2.23
     entweder
    2.11
    ITHER
    1.48
     или
    1.44
    要么
    1.41
    Activations Density 0.024%

    No Known Activations