© 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. 22-GEMMASCOPE-RES-131K
    7. 68006
    Prev
    Next
    INDEX
    Explanations

    generating information

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

    The neuron strongly activates on longer, content‐heavy (polysyllabic) 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_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
     وقال
    -0.99
    の方法
    -0.94
    ogical
    -0.94
     or
    -0.89
    采用了
    -0.89
    ilized
    -0.87
    Constructors
    -0.87
    無人
    -0.87
    lectual
    -0.86
    ItemClick
    -0.86
    POSITIVE LOGITS
     Third
    0.88
     Between
    0.87
     Diese
    0.86
    縷
    0.84
     Red
    0.83
     Total
    0.82
     quedando
    0.82
    ですが
    0.81
     З
    0.80
     The
    0.80
    Activations Density 0.058%

    No Known Activations