© 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. 31994
    Prev
    Next
    INDEX
    Explanations

    legal case numbers or mentions

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

    The neuron activates on sequences of numeric grant or funding award identifiers (e.g., “Nos. 2016-27,” “1448 Nos. 2016YFC…”).

    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
    
    -0.74
    効
    -0.71
    lstm
    -0.69
    Mitochond
    -0.69
     bụng
    -0.68
    tempts
    -0.67
    Circuit
    -0.66
    wiąz
    -0.66
    町
    -0.66
    lala
    -0.66
    POSITIVE LOGITS
     altres
    0.86
     dequeue
    0.80
    ائص
    0.71
    Tazama
    0.71
     privilegio
    0.69
    审查
    0.68
     resonator
    0.68
     privilege
    0.68
     qubit
    0.67
     Melody
    0.66
    Activations Density 0.079%

    No Known Activations