© 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. 108686
    Prev
    Next
    INDEX
    Explanations

    making or made decisions

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

    The main thing this neuron does is detect numeric tokens (multi-digit numbers and statistics).

    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
     ahorro
    -0.81
     CREATED
    -0.81
    Ensure
    -0.79
     montaje
    -0.79
     criação
    -0.79
    憷
    -0.78
     probar
    -0.77
    niczka
    -0.76
     guapos
    -0.75
     CREATE
    -0.73
    POSITIVE LOGITS
     make
    5.44
     making
    5.31
     makes
    4.38
    Making
    4.34
     made
    4.34
     Making
    3.92
    making
    3.92
    make
    3.86
    Make
    3.75
     Make
    3.34
    Activations Density 0.203%

    No Known Activations