© 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. 8543
    Prev
    Next
    INDEX
    Explanations

    informant

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

    The neuron fires on tokens that appear in parenthetical definitions or clarifications (e.g. “(known as the ‘household respondent’)”), i.e. it marks parenthesized definitional phrases.

    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
    ässä
    -0.85
     نوش
    -0.84
     experimenter
    -0.77
     thermomix
    -0.76
     Invasive
    -0.75
     conqueror
    -0.75
    ⁡
    -0.72
     Changer
    -0.71
     Inscription
    -0.71
     winners
    -0.71
    POSITIVE LOGITS
     informant
    3.36
     informants
    3.28
    inform
    2.94
     Inform
    2.92
     inform
    2.81
    Inform
    2.73
     informer
    1.98
     sources
    1.84
     информа
    1.84
     informing
    1.83
    Activations Density 0.031%

    No Known Activations