© 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. 34-GEMMASCOPE-RES-131K
    7. 84512
    Prev
    Next
    INDEX
    Explanations

    as a function of

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

    The neuron fires on the phrasing that introduces measured dependencies, most characteristically the “as a function of” construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    manuelle
    -0.74
     Aucune
    -0.74
    ][$
    -0.73
    []{"
    -0.72
    goyle
    -0.72
     Represents
    -0.71
    дини
    -0.70
     pettico
    -0.70
    mbggenerated
    -0.70
     Thro
    -0.70
    POSITIVE LOGITS
     function
    3.61
     functions
    2.88
    function
    2.73
     функ
    2.30
    函数
    2.28
     Function
    2.27
    functions
    2.25
     función
    2.25
     функция
    2.17
     funzione
    2.14
    Activations Density 0.036%

    No Known Activations