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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110462
    Prev
    Next
    INDEX
    Explanations

    university admissions and visits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ClInclude
    -0.80
    erts
    -0.75
    上课
    -0.75
    idus
    -0.74
    мин
    -0.72
    ubei
    -0.72
    لیت
    -0.71
    ORDERS
    -0.71
     tanul
    -0.71
    orders
    -0.70
    POSITIVE LOGITS
     admissions
    2.38
     Admissions
    2.28
    Admissions
    2.08
     prospective
    1.80
     admission
    1.75
     Prospective
    1.62
     Admission
    1.58
     visit
    1.44
     tours
    1.41
    Admission
    1.41
    Activations Density 0.029%

    No Known Activations