© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109459
    Prev
    Next
    INDEX
    Explanations

    education qualifications and frameworks

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

    The neuron robustly fires on formal educational or curriculum‐design jargon (e.g. learning outcomes, assessment criteria, programme specifications).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    اريخ
    -0.76
    delà
    -0.74
     тари
    -0.71
    娩
    -0.71
    enderita
    -0.70
    коны
    -0.69
     still
    -0.69
     HUD
    -0.68
     schick
    -0.67
    Tristan
    -0.67
    POSITIVE LOGITS
     Qualifications
    1.33
     qualification
    1.16
     Framework
    1.16
    Qualifications
    1.09
     Qualification
    1.08
     qualifications
    1.04
    Framework
    1.02
     EQ
    0.98
     framework
    0.98
     validation
    0.89
    Activations Density 0.018%

    No Known Activations