© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107238
    Prev
    Next
    INDEX
    Explanations

    student and student leader roles

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

    The neuron flags mentions of universities collecting or allocating student fees.

    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
    Professor
    -0.88
     embraces
    -0.82
    orthy
    -0.80
     admission
    -0.77
    তা
    -0.77
     рассе
    -0.76
     блюда
    -0.75
     Ornament
    -0.75
     Affidavit
    -0.75
     flushed
    -0.75
    POSITIVE LOGITS
     Student
    1.63
     student
    1.47
    Student
    1.34
     Students
    1.22
     senators
    1.17
     Senate
    1.13
     STUDENT
    1.07
    Senate
    1.03
    student
    1.03
    STUDENT
    0.99
    Activations Density 0.018%

    No Known Activations