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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12413
    Prev
    Next
    INDEX
    Explanations

    academic programs and fields

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

    The neuron fires on names of academic departments, majors, and professional/educational program titles.

    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
     that
    -1.54
    雋
    -1.31
    ってない
    -1.26
     “(
    -1.23
    াত
    -1.22
    '
    -1.20
     it
    -1.20
     amarilla
    -1.13
     madura
    -1.12
     简介
    -1.12
    POSITIVE LOGITS
    ARS
    1.53
    </i>
    1.52
     we
    1.41
     have
    1.39
     instead
    1.36
    ୩
    1.35
    
    1.34
    </em>
    1.33
     моя
    1.32
     visualización
    1.30
    Activations Density 0.040%

    No Known Activations