© 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. 116125
    Prev
    Next
    INDEX
    Explanations

    graphics drawing functions

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

    The neuron is triggered primarily by numeric literal tokens (e.g. standalone numbers 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
     their
    -1.16
    ශ
    -0.90
     these
    -0.89
     this
    -0.85
     while
    -0.84
     any
    -0.82
     both
    -0.81
     all
    -0.81
     that
    -0.79
     with
    -0.78
    POSITIVE LOGITS
    uthor
    0.99
     Ery
    0.95
    fficients
    0.84
    
    0.81
    orst
    0.81
    ʵ
    0.80
     advers
    0.78
    uws
    0.78
    institution
    0.77
    gewiesen
    0.77
    Activations Density 0.001%

    No Known Activations