© 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. 66553
    Prev
    Next
    INDEX
    Explanations

    physical confrontation and retaliation

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

    The neuron strongly responds to first-person, self-referential narrative or dialogue (e.g. “I,” “my,” quoted speech).

    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
     Eichen
    -1.05
    хами
    -1.00
    meros
    -0.97
    మి
    -0.97
    ocios
    -0.97
    centaje
    -0.94
    Ṇ
    -0.94
     memutus
    -0.93
     pesanan
    -0.93
     ſee
    -0.92
    POSITIVE LOGITS
     retali
    1.02
     retaliation
    0.97
     attack
    0.91
     shoot
    0.90
    身の
    0.85
     launch
    0.84
     launched
    0.80
     underestimated
    0.79
     threatened
    0.79
     Kins
    0.77
    Activations Density 0.034%

    No Known Activations