© 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. 92937
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    This neuron detects lines with unusually deep indentation (large blocks of leading whitespace).

    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
     What
    -1.38
     what
    -1.31
     How
    -1.17
     Why
    -1.13
    What
    -1.13
     how
    -1.09
     still
    -1.09
     Amazing
    -1.05
     really
    -1.03
     Nasıl
    -1.03
    POSITIVE LOGITS
     konusunda
    1.12
    这两
    1.09
    เพิ่ม
    1.06
    abetes
    1.05
    ígeno
    1.04
     peo
    1.04
     nigra
    1.03
     beij
    1.02
    Nimbus
    1.02
     abo
    1.02
    Activations Density 0.003%

    No Known Activations