© 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. 464
    Prev
    Next
    INDEX
    Explanations

    list indexing within loops

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

    The neuron fires on square‐bracket array indexing expressions.

    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
     سایر
    -1.13
     查看
    -1.11
    earned
    -1.07
    having
    -1.07
     contribuer
    -1.04
    {}'.
    -1.02
    вою
    -1.01
     того
    -1.00
     других
    -0.99
     into
    -0.98
    POSITIVE LOGITS
     =
    1.24
     is
    1.22
     bukanlah
    1.12
    들은
    1.07
    Комплек
    0.99
     artistique
    0.99
    ógicos
    0.97
     scattata
    0.96
     was
    0.95
     this
    0.94
    Activations Density 0.004%

    No Known Activations