© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72675
    Prev
    Next
    INDEX
    Explanations

    lists of topics

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

    The neuron specializes in spotting words and phrases typical of click-bait or listicle headlines (e.g. “You Need To,” numbered “Top ____,” “Signs You Might,” “Best ____ to ____,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     such
    -1.61
     SISTEMA
    -1.30
     many
    -1.25
     allah
    -1.10
     something
    -1.09
     hvordan
    -1.08
     advir
    -1.08
     ayam
    -1.08
     området
    -1.05
     gita
    -1.05
    POSITIVE LOGITS
     you
    1.48
     your
    1.28
    全都
    1.05
     τελευτα
    0.97
     آن‌ها
    0.96
     inférieur
    0.95
     según
    0.94
     лента
    0.94
     листо
    0.94
     mejorando
    0.93
    Activations Density 0.054%

    No Known Activations