© 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. 13771
    Prev
    Next
    INDEX
    Explanations

    different ways of being

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

    The neuron fires on words that express variety or multiplicity—tokens like “different,” “multiple,” “various,” “fragmented,” etc.

    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
     früher
    -1.04
     also
    -0.98
     saturated
    -0.93
    早めに
    -0.92
    詳しい
    -0.91
     former
    -0.88
    じっくり
    -0.87
    icular
    -0.87
     earlier
    -0.86
     также
    -0.85
    POSITIVE LOGITS
     different
    2.16
     olika
    1.55
     disparate
    1.51
     différentes
    1.49
     inconsistent
    1.49
     diferite
    1.47
     farklı
    1.45
     różne
    1.41
     разных
    1.41
     różnych
    1.41
    Activations Density 0.123%

    No Known Activations