© 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. 10-GEMMASCOPE-RES-131K
    7. 58452
    Prev
    Next
    INDEX
    Explanations

    high school

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

    The main thing this neuron does is detect mentions of the phrase “high school.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    を行います
    -2.20
    带上
    -2.17
    ?
    -2.14
    閦
    -2.02
      
    -2.02
    .’
    -1.99
    1
    -1.96
    虽说
    -1.94
    直至
    -1.93
     However
    -1.92
    POSITIVE LOGITS
    忸
    2.08
    ꦫ
    2.02
    觔
    1.98
     confronti
    1.97
     perbaikan
    1.96
    蛩
    1.96
     ponú
    1.95
     間取り
    1.94
     buvo
    1.94
    comuna
    1.90
    Activations Density 0.011%

    No Known Activations