© 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. 2144
    Prev
    Next
    INDEX
    Explanations

    build directory outputs

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

    The neuron activates on tokens containing numeric digits (i.e. any digit-heavy token).

    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
    Residence
    -0.73
     izquierdo
    -0.73
    domaine
    -0.71
    demort
    -0.70
     scott
    -0.70
     mask
    -0.70
     stdin
    -0.69
     BASIS
    -0.68
    Preface
    -0.68
     seed
    -0.68
    POSITIVE LOGITS
     build
    1.89
    build
    1.79
     output
    1.76
     outputs
    1.54
    dist
    1.47
    output
    1.46
     builds
    1.45
     dist
    1.38
     out
    1.35
    Build
    1.34
    Activations Density 0.113%

    No Known Activations