© 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. 34-GEMMASCOPE-RES-131K
    7. 78902
    Prev
    Next
    INDEX
    Explanations

    tips, guides, and lessons

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

    The neuron fires on content‐bearing, capitalized words that form part of headings or product/course titles in sales or instructional 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
     of
    -0.96
    volent
    -0.89
    portál
    -0.86
    archiw
    -0.85
    rafat
    -0.84
    aéroport
    -0.84
     rezerv
    -0.83
    Visita
    -0.83
     また
    -0.83
     craindre
    -0.82
    POSITIVE LOGITS
     tips
    1.81
    tips
    1.53
     secrets
    1.50
     guide
    1.48
     essentials
    1.39
     basics
    1.38
     techniques
    1.36
     Tips
    1.36
     strategies
    1.35
    Tips
    1.35
    Activations Density 0.072%

    No Known Activations