© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60241
    Prev
    Next
    INDEX
    Explanations

    instant outcomes and services

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

    The neuron detects instances of the word “instant” (and its immediate‐action variants like “instantly,” “immediate,” etc.), i.e. language signalling immediacy.

    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
    }$
    -1.66
    弍
    -1.63
     Ähn
    -1.61
    蛲
    -1.61
     tain
    -1.59
    盦
    -1.54
     テーブル
    -1.52
     fazendo
    -1.52
     ????
    -1.50
     the
    -1.48
    POSITIVE LOGITS
     Она
    2.14
    Getting
    1.63
    Now
    1.63
    Give
    1.62
    इटम
    1.59
    Have
    1.58
    Having
    1.55
    Instant
    1.55
     Instant
    1.53
     gratification
    1.53
    Activations Density 0.018%

    No Known Activations