© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31413
    Prev
    Next
    INDEX
    Explanations

    discussing needs and methods

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

    The main thing this neuron does is find numeric expressions (tokens representing numbers or measured quantities) in the text.

    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
    规律
    -1.01
     expliquer
    -1.00
     Structures
    -1.00
    LAURA
    -0.99
    挿入
    -0.98
    Methodology
    -0.95
     Demographics
    -0.93
     topographical
    -0.93
     đà
    -0.92
    CHARLES
    -0.92
    POSITIVE LOGITS
     managers
    1.36
     manager
    1.20
     management
    1.08
    Synthesis
    1.06
    Science
    0.99
     integrative
    0.98
     synthesis
    0.96
    managers
    0.95
    脊
    0.94
     suites
    0.92
    Activations Density 0.089%

    No Known Activations