© 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. 70523
    Prev
    Next
    INDEX
    Explanations

    mixture of materials

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

    The neuron activates on mentions of a “mixture,” i.e. references to combining or blending multiple components.

    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
    埽
    -3.61
     ausein
    -3.25
    镦
    -2.83
     dengan
    -2.70
    
    -2.63
    檠
    -2.63
    ᷆
    -2.59
     עם
    -2.59
    栊
    -2.58
    鯪
    -2.56
    POSITIVE LOGITS
    ↵
    3.23
     
    3.19
    .
    2.84
     Their
    2.73
    除此之外
    2.64
     “
    2.61
    ↵↵
    2.58
    ’
    2.58
     Other
    2.56
    与此同时
    2.53
    Activations Density 0.021%

    No Known Activations