© 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. 107532
    Prev
    Next
    INDEX
    Explanations

    the word

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

    The neuron activates when the text is talking about a word itself—especially in metalinguistic phrases like “the word ‘…’.”

    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
     hausse
    -1.24
    oping
    -1.15
    extremely
    -1.05
     chuť
    -1.03
     ();
    -1.02
     MAKING
    -1.01
    荭
    -1.00
    ourced
    -0.99
    really
    -0.99
     ].
    -0.97
    POSITIVE LOGITS
     meticulous
    1.02
     immaculate
    0.95
     substantial
    0.95
     suggests
    0.93
    单词
    0.92
     flimsy
    0.90
     entails
    0.90
     encompasses
    0.88
     nestled
    0.86
     daunting
    0.86
    Activations Density 0.036%

    No Known Activations