© 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. 22-GEMMASCOPE-RES-131K
    7. 70396
    Prev
    Next
    INDEX
    Explanations

    indefinite pronouns

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

    The neuron is triggered by non-specific indefinite pronouns or quantifiers (e.g. “something,” “anything,” “everything”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.36
    良かったです
    -1.01
    живание
    -1.00
    Penjelasan
    -0.94
    的一
    -0.92
    ۔۔
    -0.90
     Smack
    -0.90
    為了
    -0.88
     downvotes
    -0.88
     numerosos
    -0.86
    POSITIVE LOGITS
     from
    1.17
     everyone
    1.06
    ТЕЛЬ
    1.02
     pureza
    0.99
    昵称
    0.99
     here
    0.98
    tectable
    0.97
     tutaj
    0.96
     civiles
    0.94
    男朋友
    0.94
    Activations Density 0.061%

    No Known Activations