© 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. 34-GEMMASCOPE-RES-131K
    7. 59712
    Prev
    Next
    INDEX
    Explanations

    immutable data structures

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

    The neuron detects mentions of immutable data structures or the concept of immutability.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ventricle
    -0.84
     Pct
    -0.81
    əsi
    -0.80
    んでいた
    -0.79
    百分之
    -0.76
    Açık
    -0.76
    cterms
    -0.75
    meteries
    -0.75
    ultuous
    -0.75
    Demografía
    -0.74
    POSITIVE LOGITS
    setStyle
    0.85
     Immutable
    0.77
    וס
    0.76
     nij
    0.76
    grub
    0.72
    ochrom
    0.71
    GEO
    0.71
    在我们
    0.70
    znál
    0.70
     pö
    0.69
    Activations Density 0.002%

    No Known Activations