© 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. 10-GEMMASCOPE-RES-131K
    7. 23862
    Prev
    Next
    INDEX
    Explanations

    the extent to which

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

    This neuron detects phrases that introduce a quantified scope of investigation—particularly “extent to which” (and similar “degree to which”) constructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    noo
    -1.70
    🫅
    -1.66
     paisajes
    -1.63
     autorizado
    -1.62
     semblable
    -1.56
    鼕
    -1.56
    ﻂ
    -1.55
    鷙
    -1.55
    
    -1.55
     músculos
    -1.53
    POSITIVE LOGITS
    6
    1.88
    需要
    1.87
    s
    1.87
    2
    1.87
     you
    1.78
    你
    1.73
     -
    1.73
    kes
    1.71
    er
    1.71
    www
    1.70
    Activations Density 0.012%

    No Known Activations