© 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. 10-GEMMASCOPE-RES-131K
    7. 9755
    Prev
    Next
    INDEX
    Explanations

    struck with impact or realization

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

    The neuron specifically detects the past-tense verb “struck.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    橚
    -2.92
    0
    -2.52
    ⢓
    -2.45
    ではまた
    -2.45
    红色的
    -2.45
     sonriendo
    -2.44
    他の
    -2.42
    葙
    -2.42
    ING
    -2.39
    
    -2.39
    POSITIVE LOGITS
    ’
    3.16
     Now
    3.14
     This
    2.77
    '
    2.73
    s
    2.61
     They
    2.50
    NOSIS
    2.44
    ]));
    2.41
     alongside
    2.41
     };
    2.41
    Activations Density 0.004%

    No Known Activations