© 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. 87027
    Prev
    Next
    INDEX
    Explanations

    Hansen Brothers or ssl context

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

    This neuron fires strongly on uncommon or domain‐specific tokens—particularly proper names (like "Hansen") and acronyms/technical abbreviations (e.g., "InlineData", "ssl", "nul" from “nullifies”)—i.e. rare tokens rather than common words.

    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
    o
    -4.09
    ↵↵
    -3.42
    </h2>
    -3.00
    h
    -2.98
    “
    -2.88
    倘
    -2.81
     pesky
    -2.73
    d
    -2.67
     rampant
    -2.55
    ''
    -2.52
    POSITIVE LOGITS
    埽
    2.83
    which
    2.81
    
    2.73
     javas
    2.69
    䛗
    2.67
    唖
    2.67
    どんどん
    2.67
    楽しみに
    2.56
    」　
    2.53
    栳
    2.53
    Activations Density 0.018%

    No Known Activations