© 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. 105852
    Prev
    Next
    INDEX
    Explanations

    binary choice and selection

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

    The main thing this neuron does is spot technical econometric terminology and model‐specification terms (e.g. endogenous variable, probit, IV, 2SLS).

    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
     which
    -1.42
     Downloader
    -1.09
     especies
    -1.09
     diámetro
    -1.08
     Installer
    -1.07
    ×</
    -1.07
     entwickelte
    -1.06
    ductors
    -1.06
    oluzione
    -1.05
    from
    -1.05
    POSITIVE LOGITS
    částí
    1.16
     protegida
    1.11
     Entrepreneurs
    1.09
     hué
    1.09
    ּוֹ
    1.08
    melody
    1.07
    Então
    1.06
    ΤΟ
    1.05
     Ağustos
    1.05
    illow
    1.05
    Activations Density 0.105%

    No Known Activations