© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32079
    Prev
    Next
    INDEX
    Explanations

    location coordinates

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

    The neuron is picking up numeric literals (individual digits and multi‐digit numbers) in source 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
    зме
    -0.90
     idag
    -0.86
     uVar
    -0.77
    paque
    -0.77
    ίδ
    -0.76
     desmotiv
    -0.76
     летом
    -0.76
    unjang
    -0.74
     gomma
    -0.72
    קרי
    -0.71
    POSITIVE LOGITS
     location
    0.96
     coordinates
    0.95
    tető
    0.90
     Coordinates
    0.90
     Avenger
    0.89
    ocation
    0.88
    Vector
    0.86
     beacon
    0.85
     Vector
    0.84
     coords
    0.84
    Activations Density 0.001%

    No Known Activations