© 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. 68427
    Prev
    Next
    INDEX
    Explanations

    node pointer access

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

    The neuron fires on code tokens that name or instantiate types—e.g. class names and constructor calls (CamelCase identifiers like Node, MyStream, etc.)

    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
     informazioni
    -1.08
     melawan
    -1.00
    Màu
    -0.96
    пратки
    -0.96
     internetowa
    -0.96
    phòng
    -0.95
    え
    -0.94
    翳
    -0.94
    niña
    -0.93
    țele
    -0.92
    POSITIVE LOGITS
     is
    0.95
    ("#{
    0.92
    -
    0.90
    CÓ
    0.88
     philosophie
    0.88
     devra
    0.88
    閨
    0.87
     yesterday
    0.84
     αὐτ
    0.84
     last
    0.84
    Activations Density 0.006%

    No Known Activations