© 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. 74956
    Prev
    Next
    INDEX
    Explanations

    other languages

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

    The neuron responds strongly to scientific enumerations—especially numeric list markers and chemical or biochemical terms (e.g. sugar names, pH, electrolyte measurements).

    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
    fand
    -0.90
    lename
    -0.86
     same
    -0.84
     that
    -0.83
     back
    -0.81
     up
    -0.80
     reserved
    -0.77
    ._.
    -0.77
     at
    -0.76
    technologies
    -0.76
    POSITIVE LOGITS
     other
    2.09
    その他
    1.84
     अन्य
    1.74
     autres
    1.70
    其他
    1.62
    Other
    1.61
    其它
    1.58
     других
    1.57
    other
    1.53
     diğer
    1.53
    Activations Density 0.060%

    No Known Activations