© 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. 58819
    Prev
    Next
    INDEX
    Explanations

    pivot, pivotable, pivoting

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

    The neuron detects occurrences of “pivot” (and its close variants like Pivotal, pivotable, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Bahkan
    -0.79
    formations
    -0.79
    eradish
    -0.77
     nächste
    -0.76
    ies
    -0.75
     Beberapa
    -0.75
    Via
    -0.75
    entuan
    -0.74
    feed
    -0.73
     Selanjutnya
    -0.71
    POSITIVE LOGITS
     pivot
    1.23
    pivot
    1.16
     piv
    1.14
     Pivot
    1.06
     Piv
    1.02
     pivo
    0.97
    piv
    0.91
    Pivot
    0.90
    ьаж
    0.79
    طقة
    0.79
    Activations Density 0.014%

    No Known Activations