© 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. 10-GEMMASCOPE-RES-131K
    7. 103022
    Prev
    Next
    INDEX
    Explanations

    military and educational institutions

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

    The neuron detects mentions of “Academy” in proper names, especially military or service academies.

    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
     here
    -1.30
    ꯢ
    -1.23
     there
    -1.17
     We
    -1.16
     aquí
    -1.09
    vero
    -1.09
     电视
    -1.09
    -“
    -1.08
     Weisheit
    -1.08
    fontWeight
    -1.05
    POSITIVE LOGITS
     on
    1.27
     espiritual
    1.23
     authorization
    1.22
     from
    1.20
    y
    1.17
    لاً
    1.16
    やった
    1.15
    值为
    1.15
     üzerinden
    1.13
     Электро
    1.13
    Activations Density 0.049%

    No Known Activations