© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62520
    Prev
    Next
    INDEX
    Explanations

    certifications and training

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

    This neuron flags mentions of formal technology product or certification names (e.g. uppercase or title-case vendor, program, or exam titles).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     ([]
    -0.89
     phoenix
    -0.85
     חיצוני
    -0.85
    瘻
    -0.82
    ッセイ
    -0.82
    慙
    -0.80
     applauded
    -0.80
     aſ
    -0.79
     rezerv
    -0.79
     apparten
    -0.77
    POSITIVE LOGITS
     Fundamentals
    1.30
     course
    1.22
     básico
    1.20
     theory
    1.13
     skills
    1.08
     basics
    1.07
     Level
    1.05
     barista
    1.04
     Specialist
    1.02
     qualification
    1.02
    Activations Density 0.043%

    No Known Activations