© 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. 90464
    Prev
    Next
    INDEX
    Explanations

    directional movement

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

    The neuron activates on numeric tokens (e.g., digits, numeric literals, or enum values) 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
    belea
    -1.02
    cillos
    -0.88
    barung
    -0.87
    cteur
    -0.84
    HING
    -0.83
    فیلم
    -0.83
    спользование
    -0.81
    ceğiniz
    -0.81
    ずら
    -0.80
    technologie
    -0.80
    POSITIVE LOGITS
     left
    2.78
     up
    2.09
     right
    2.02
     Left
    2.02
    left
    1.96
     LEFT
    1.93
     down
    1.92
    Left
    1.84
    LEFT
    1.70
     Up
    1.65
    Activations Density 0.035%

    No Known Activations