© 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. 34-GEMMASCOPE-RES-131K
    4. 70138
    Prev
    Next
    INDEX
    Explanations

    Simple

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

    The neuron fires on occurrences of the word “simple” (and its case variants) in the text.

    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
    糁
    -1.08
     verschillende
    -1.03
    に対して
    -1.02
     preparando
    -1.02
     nieuwe
    -1.01
     famoso
    -1.01
     immense
    -0.98
     absolut
    -0.97
     سرا
    -0.94
     bizarre
    -0.93
    POSITIVE LOGITS
    ton
    2.16
     simple
    2.09
     but
    2.08
    Simple
    1.88
     straightforward
    1.88
     yet
    1.76
    simple
    1.72
     pleasures
    1.70
    minded
    1.67
    tons
    1.62
    Activations Density 0.061%

    No Known Activations