© 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. 118214
    Prev
    Next
    INDEX
    Explanations

    recognition

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

    The neuron strongly activates on occurrences of the word “recognition” (and its morphological variants like “recognized” or “unrecognized”).

    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
    )
    -1.49
    ),
    -1.24
     When
    -1.20
     Why
    -1.18
     to
    -1.09
     use
    -1.05
     مکان
    -1.05
    ]
    -1.02
    .
    -1.02
    讴
    -1.01
    POSITIVE LOGITS
     Recogn
    1.86
     recognizes
    1.77
     Recognition
    1.77
     recognise
    1.63
    recogn
    1.59
     recognition
    1.57
     RECOGN
    1.52
    recognize
    1.50
     recog
    1.49
     reconnaît
    1.48
    Activations Density 0.020%

    No Known Activations