© 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. 73881
    Prev
    Next
    INDEX
    Explanations

    people following verbs

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

    The neuron consistently fires on words that refer to people or groups of people (e.g. “anyone,” “who,” “people,” “audience,” “guys,” “everybody”).

    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
     erneut
    -1.44
    Какво
    -1.37
     также
    -1.28
     лишь
    -1.27
     maakte
    -1.20
     également
    -1.16
     FUCK
    -1.14
    Each
    -1.14
    Soon
    -1.14
     “…
    -1.13
    POSITIVE LOGITS
     kind
    2.28
     really
    2.16
     maybe
    2.03
     somebody
    2.00
     everybody
    1.97
     [
    1.96
     sort
    1.92
     basically
    1.90
     actually
    1.73
     probably
    1.73
    Activations Density 0.022%

    No Known Activations