© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9616
    Prev
    Next
    INDEX
    Explanations

    Revival style, known bird, CNT, financial $

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

    The neuron is a detector for unusually long, multi‐syllable “technical” words (e.g. phytoremediation, dividend yield, solutions).

    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
     zwölf
    -0.96
    Huhu
    -0.92
    ,
    -0.90
     рецепта
    -0.89
    どうなる
    -0.88
     Freunden
    -0.88
    傒
    -0.86
     interessiert
    -0.86
    câ
    -0.84
    plish
    -0.83
    POSITIVE LOGITS
    hever
    1.15
     territ
    0.97
     纹理
    0.97
    Ꭼ
    0.94
     tı
    0.92
     позволя
    0.92
     \\
    
    0.90
    ഓ
    0.90
    Người
    0.89
    Υ
    0.89
    Activations Density 0.044%

    No Known Activations