© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27824
    Prev
    Next
    INDEX
    Explanations

    array and assoc

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

    This neuron detects references to array‐fetching functions or array constructs (e.g. “fetch_array,” “fetch_assoc,” “array”) 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
    com
    -1.33
     and
    -1.26
     eventually
    -1.17
    om
    -1.16
    ac
    -1.16
    T
    -1.14
     finally
    -1.14
     set
    -1.13
    ga
    -1.13
    <h2>
    -1.13
    POSITIVE LOGITS
     nór
    1.53
    oquia
    1.41
     interesado
    1.36
     pintadas
    1.32
     oignon
    1.27
     mundiales
    1.27
    پاسخ
    1.27
    🧶
    1.26
     secado
    1.26
     rús
    1.26
    Activations Density 0.000%

    No Known Activations