© 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. 87255
    Prev
    Next
    INDEX
    Explanations

    leadership and teamwork

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

    The neuron strongly activates on document section headings or titles (especially numbered or title‐case phrases).

    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
    Litteratur
    -0.92
    ݨ
    -0.92
    föra
    -0.91
    Ỹ
    -0.90
    fetchall
    -0.87
     belki
    -0.85
     melanjutkan
    -0.82
     måte
    -0.81
     innehå
    -0.81
    ၽ
    -0.79
    POSITIVE LOGITS
     praise
    1.47
     listen
    1.34
     listening
    1.34
     coach
    1.28
     lead
    1.27
     delegate
    1.24
     coaching
    1.23
     reward
    1.22
     transparent
    1.21
     listens
    1.20
    Activations Density 0.012%

    No Known Activations