© 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. 22-GEMMASCOPE-RES-131K
    7. 12943
    Prev
    Next
    INDEX
    Explanations

    basic concepts

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

    This neuron detects hedging or speculative conditional phrasing (e.g. words like “if,” “that,” “unlikely,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     perfeito
    -0.82
     abstrato
    -0.79
    อาจ
    -0.73
    ursa
    -0.72
    irà
    -0.71
    unzione
    -0.70
     may
    -0.70
    ಾಗಿ
    -0.70
    cean
    -0.69
    országban
    -0.69
    POSITIVE LOGITS
     basic
    1.34
    basic
    1.23
    Basic
    1.15
     Basic
    1.11
     fundamental
    1.07
     базо
    1.07
     基本
    1.05
     essentials
    1.05
     BASIC
    1.03
    的基本
    1.03
    Activations Density 0.060%

    No Known Activations