© 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. 97731
    Prev
    Next
    INDEX
    Explanations

    hindu temples and puranas

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

    The neuron fires on brief, typically three‐letter, capitalized tokens (including short name fragments or acronyms, as well as Unicode/escape sequences).

    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
    声が
    -0.98
     vina
    -0.88
    が
    -0.85
    Agr
    -0.85
    繋がり
    -0.84
    гости
    -0.83
     Op
    -0.81
     angling
    -0.81
     sino
    -0.81
    となった
    -0.81
    POSITIVE LOGITS
     chociaż
    0.99
    やう
    0.96
     Nevertheless
    0.90
     Krzysz
    0.87
     Rücksicht
    0.86
    なんですね
    0.85
     abbin
    0.84
     fornis
    0.84
    nová
    0.84
    んですよね
    0.83
    Activations Density 0.003%

    No Known Activations