© 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. 10-GEMMASCOPE-RES-131K
    7. 19646
    Prev
    Next
    INDEX
    Explanations

    bikini or chrono

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

    The neuron fires on low‐frequency, specialized tokens—words like “GenerationType,” “chrono,” “bikini,” or “leaderboard” that stand out as rare or domain‐specific terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    न
    -2.63
    AT
    -2.19
    u
    -2.16
    AL
    -2.14
    鸶
    -2.08
     be
    -2.08
    AN
    -2.05
    AD
    -2.02
    莚
    -1.98
     使っ
    -1.96
    POSITIVE LOGITS
     MOST
    2.52
    馕
    2.25
    噲
    2.14
    愎
    2.08
    
    2.02
     Eighty
    1.97
     mitte
    1.94
     évé
    1.94
    0
    1.93
    搂
    1.92
    Activations Density 0.004%

    No Known Activations