© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101931
    Prev
    Next
    INDEX
    Explanations

    evidence and proof

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

    The neuron detects references to empirical scientific terms—words like data, evidence, observations, experiments, and related concepts.

    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
     for
    -1.84
    ByDefault
    -1.54
     when
    -1.46
     if
    -1.39
     had
    -1.38
     werd
    -1.37
    :['
    -1.34
     jika
    -1.34
     „
    -1.33
    愉
    -1.30
    POSITIVE LOGITS
     that
    1.69
    れてる
    1.45
    曖昧さ回避
    1.30
     الفلسط
    1.25
    する方法
    1.23
    outros
    1.22
     に関する
    1.22
     verstor
    1.21
    知り
    1.20
    メルカリ
    1.20
    Activations Density 0.226%

    No Known Activations