© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103031
    Prev
    Next
    INDEX
    Explanations

    associated with

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

    The neuron detects language signaling statistical relationships or associations in study reports (e.g. “whether … were associated,” “associated with,” “predictors of,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    *}\
    -1.48
    *}$
    -1.48
     =
    -1.45
    很多
    -1.34
    .},
    -1.34
     provavelmente
    -1.33
     témo
    -1.30
     }^{
    -1.27
     что
    -1.26
    oused
    -1.26
    POSITIVE LOGITS
     with
    2.06
     of
    1.83
     using
    1.62
     its
    1.58
     if
    1.34
    őzés
    1.34
     or
    1.33
    我们就
    1.31
     during
    1.30
     different
    1.26
    Activations Density 1.529%

    No Known Activations