© 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. 97856
    Prev
    Next
    INDEX
    Explanations

    after school activities

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

    The main thing this neuron does is spot mentions of organized educational or youth‐development offerings—like “after-school programs,” tutoring roles, job/volunteer opportunities, and related field listings.

    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
    instant
    -0.72
     الحديث
    -0.71
     roommates
    -0.71
    spół
    -0.70
    allan
    -0.69
    ≈
    -0.68
     expedite
    -0.68
    <code>
    -0.68
    エム
    -0.68
    ஹ
    -0.67
    POSITIVE LOGITS
     after
    2.05
    after
    1.72
     After
    1.68
    After
    1.65
     enrichment
    1.45
     club
    1.45
     before
    1.41
     clubs
    1.34
    richment
    1.33
     после
    1.32
    Activations Density 0.018%

    No Known Activations