© 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. 105183
    Prev
    Next
    INDEX
    Explanations

    reality is that

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

    This neuron detects emphatic introductory phrases that state a fact or reality—e.g. “the fact is,” “the truth is,” “the reality is,” or “the ugly truth is.”

    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
    knex
    -1.63
     Besonder
    -1.56
    ",
    
    -1.52
    "",
    
    -1.50
    ?"
    -1.48
    "।
    -1.48
    ()?.
    -1.44
     including
    -1.43
    )"
    -1.41
    ouest
    -1.36
    POSITIVE LOGITS
     that
    1.63
     большин
    1.57
    それでは
    1.53
    ホ
    1.52
    ーーーー
    1.48
    キ
    1.45
    ここの
    1.44
     всі
    1.44
    ーーー
    1.43
    きゃ
    1.42
    Activations Density 0.015%

    No Known Activations