© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32170
    Prev
    Next
    INDEX
    Explanations

    federal student financial aid

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

    The neuron strongly activates on passages dealing with financial topics—particularly mentions of “financial” and related money, scholarship, or loan terms.

    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
    yoo
    -0.76
    ખ
    -0.75
     Jacoby
    -0.73
    ggg
    -0.71
     Vlas
    -0.70
    crap
    -0.69
    isla
    -0.68
    pade
    -0.68
     pratos
    -0.68
    fürst
    -0.68
    POSITIVE LOGITS
     aid
    1.65
     Pell
    1.59
     Financial
    1.53
     financial
    1.49
     Aid
    1.45
     federal
    1.39
     Federal
    1.37
    Financial
    1.27
     award
    1.21
     student
    1.18
    Activations Density 0.013%

    No Known Activations