© 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. 80750
    Prev
    Next
    INDEX
    Explanations

    structural equation modeling techniques

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

    The neuron primarily responds to numeric tokens and other high-magnitude values—e.g. large counts, years, sample sizes, and model-parameter numbers.

    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
    hanging
    -0.79
     داخ
    -0.75
    provo
    -0.75
    働く
    -0.72
    れた
    -0.72
     saha
    -0.71
    Landing
    -0.69
     pazienti
    -0.69
     COMING
    -0.68
    aley
    -0.68
    POSITIVE LOGITS
     PLS
    1.31
    PLS
    1.24
     confir
    1.05
     formative
    1.02
     reflective
    1.00
    AMOS
    0.93
     Hair
    0.92
     CFA
    0.90
    CFA
    0.89
     construct
    0.89
    Activations Density 0.089%

    No Known Activations