© 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. 34-GEMMASCOPE-RES-131K
    4. 75980
    Prev
    Next
    INDEX
    Explanations

    property registration and typing

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

    The neuron fires on standalone numeric literals (whole‐number digit tokens) 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_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
     наиболее
    -0.97
    ěj
    -0.83
     convivial
    -0.82
    लिखित
    -0.75
    🏂
    -0.74
     дыха
    -0.73
     registre
    -0.73
    辛い
    -0.73
     roach
    -0.72
    quing
    -0.71
    POSITIVE LOGITS
    :@"
    0.94
    ("
    0.93
     ();
    0.89
     ["
    0.88
    uró
    0.87
     tropicales
    0.87
    :#
    0.85
    >`;
    0.84
    ();
    0.83
     ස
    0.82
    Activations Density 0.001%

    No Known Activations