© 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. 81684
    Prev
    Next
    INDEX
    Explanations

    applying for jobs or programs

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

    The neuron strongly activates on the preposition “for,” especially in contexts like “applying for,” “submitted for,” or “looking for.”

    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
    AUTHORIZED
    -0.86
     pagare
    -0.85
    共演
    -0.82
     agreeing
    -0.82
     relying
    -0.82
    alité
    -0.82
     deines
    -0.81
     ホイール
    -0.81
     reluctance
    -0.81
    անում
    -0.79
    POSITIVE LOGITS
     consideration
    1.59
     membership
    1.44
     admission
    1.34
    membership
    1.27
     positions
    1.25
     participation
    1.23
     inclusion
    1.23
     candidacy
    1.18
     this
    1.13
     consideró
    1.09
    Activations Density 0.062%

    No Known Activations