© 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. 42807
    Prev
    Next
    INDEX
    Explanations

    court decisions and approvals

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

    This neuron detects verbs (or parts of verbs) that express official decisions or authorizations (e.g. approve, grant, convict, allow, order).

    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
    と同じ
    -1.28
     discussione
    -1.21
    相当于
    -1.20
     был
    -1.16
    oursquare
    -1.13
    Selección
    -1.12
    ut
    -1.10
     rimasto
    -1.10
     trov
    -1.09
     composizione
    -1.09
    POSITIVE LOGITS
     coloridos
    1.15
    waren
    1.15
    ulica
    1.13
     Δι
    1.12
    Править
    1.12
    banyak
    1.11
     acteur
    1.11
     hvil
    1.09
    плата
    1.09
    masalah
    1.09
    Activations Density 0.152%

    No Known Activations