© 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. 28222
    Prev
    Next
    INDEX
    Explanations

    events occurring afterward

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

    The neuron is triggered by words denoting an ending or breakup (e.g. break up, disband, divorce, demolish).

    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
    owały
    -1.14
    ことから
    -1.09
    Compared
    -1.07
    -\\
    -1.05
    bajo
    -1.05
    both
    -1.05
    しまいます
    -1.05
    formerly
    -1.04
    starting
    -1.02
    Бележки
    -1.01
    POSITIVE LOGITS
     after
    2.69
     when
    2.03
     shortly
    2.00
     before
    1.91
     later
    1.59
     last
    1.55
     после
    1.51
     eventually
    1.48
    เมื่อ
    1.46
     during
    1.45
    Activations Density 0.048%

    No Known Activations