© 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. 22-GEMMASCOPE-RES-131K
    4. 66344
    Prev
    Next
    INDEX
    Explanations

    programming conditional statements

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

    This neuron fires on conditional control‐flow keywords (especially “if” and “else if”) in code.

    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
    ый
    -1.09
    Avenue
    -1.02
    Encontra
    -1.02
    liski
    -1.01
    cción
    -1.00
    ﺅ
    -0.98
    ificaciones
    -0.98
     innych
    -0.97
     lavorato
    -0.94
    vement
    -0.94
    POSITIVE LOGITS
     today
    1.04
     it
    0.96
    亟
    0.96
     Obwohl
    0.93
     دخترانه
    0.92
     Arzne
    0.91
     quelquefois
    0.91
     exceeding
    0.89
    和小
    0.88
     angewendet
    0.88
    Activations Density 0.003%

    No Known Activations