© 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. 49463
    Prev
    Next
    INDEX
    Explanations

    admissions and applications

    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
    mentary
    -0.76
    ->$
    -0.73
     Pliny
    -0.72
    optimized
    -0.72
    λικά
    -0.70
     Lob
    -0.69
     reproducible
    -0.69
     Asahi
    -0.68
     Framing
    -0.68
     Sitzung
    -0.68
    POSITIVE LOGITS
     offers
    1.31
     admissions
    1.26
     offer
    1.23
    Offer
    1.16
     Offer
    1.09
    applicant
    1.08
    Admissions
    1.05
    Offers
    1.04
     medicine
    1.00
     Admissions
    0.99
    Activations Density 0.012%

    No Known Activations