© 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. 50104
    Prev
    Next
    INDEX
    Explanations

    mentioning specific items

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

    This neuron fires on occurrences of the verb “mention” (and its morphological variants such as mentioning, mentioned) in the text.

    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
     announced
    -1.20
    移植
    -1.02
     assertion
    -0.99
    全
    -0.98
    ]
    -0.98
    enchymal
    -0.98
     expressions
    -0.96
     assurances
    -0.96
     kuah
    -0.95
    </
    -0.94
    POSITIVE LOGITS
     menciona
    1.56
     Mention
    1.42
     mention
    1.42
     упомина
    1.28
    Mention
    1.27
    specific
    1.21
     Specifically
    1.21
    mention
    1.18
     mentions
    1.16
    Specifically
    1.16
    Activations Density 0.029%

    No Known Activations