© 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. 34-GEMMASCOPE-RES-131K
    7. 37843
    Prev
    Next
    INDEX
    Explanations

    special place names or terms

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

    The neuron is primarily picking out uncommon subword fragments—especially those belonging to proper nouns, acronyms, or other rare/low-frequency tokens.

    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
    を
    -1.07
    などを
    -1.02
    と
    -0.90
    などの
    -0.85
    によって
    -0.81
    がある
    -0.81
    も
    -0.81
    이의
    -0.80
    jMenu
    -0.79
    などが
    -0.78
    POSITIVE LOGITS
     étroite
    1.05
     plateado
    0.96
    resas
    0.90
    alugar
    0.90
    ごとの
    0.89
     throng
    0.88
    Przed
    0.88
    tiker
    0.88
    lillah
    0.87
     Przed
    0.87
    Activations Density 0.002%

    No Known Activations