© 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. 39342
    Prev
    Next
    INDEX
    Explanations

    increase/decrease

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

    The neuron fires on tokens that indicate quantitative changes in measured values (e.g. low/high levels, increases, decreases, reductions) in scientific results.

    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
     även
    -1.59
     również
    -1.59
     également
    -1.58
     også
    -1.53
     arī
    -1.50
     also
    -1.48
     também
    -1.48
     також
    -1.40
     также
    -1.39
     myös
    -1.34
    POSITIVE LOGITS
     others
    1.14
     conversely
    1.09
     entgeg
    1.09
     quelli
    1.06
     daardoor
    0.91
    代わりに
    0.90
     daarmee
    0.90
     ones
    0.90
     viceversa
    0.85
     gleichzeitig
    0.85
    Activations Density 0.064%

    No Known Activations