© 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. 7898
    Prev
    Next
    INDEX
    Explanations

    curriculum, equilibrium, date, initial, thereto

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

    The neuron strongly fires on mentions of “curriculum” (and related educational‐program terms) in texts.

    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
    佧
    -2.94
    ꜆
    -2.81
    鶺
    -2.70
    齶
    -2.67
    
    -2.63
    蟊
    -2.56
    ):}
    -2.52
    妧
    -2.50
    媃
    -2.47
     márm
    -2.45
    POSITIVE LOGITS
    .
    3.31
    ↵↵
    2.83
    h
    2.63
    焄
    2.59
    '
    2.56
    ↵
    2.41
    i
    2.39
     людей
    2.20
    :
    2.19
    呖
    2.17
    Activations Density 0.003%

    No Known Activations