© 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. 93082
    Prev
    Next
    INDEX
    Explanations

    how things are measured

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

    The neuron activates on words and phrases that introduce or describe quantitative evaluations or measurements (e.g. measured, judged, ranked, performance, improvement).

    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
    ensburg
    -1.05
    sklä
    -0.97
    ZON
    -0.93
    Polen
    -0.93
    ėms
    -0.93
    初め
    -0.91
     通知
    -0.90
    эг
    -0.90
     Wikimédia
    -0.88
     Lucille
    -0.87
    POSITIVE LOGITS
     how
    1.59
     measure
    1.27
     anhand
    1.23
     whether
    1.19
     based
    1.16
     its
    1.16
     his
    1.09
    どれだけ
    1.08
    看他
    1.07
     measured
    1.05
    Activations Density 0.046%

    No Known Activations