© 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. 22-GEMMASCOPE-RES-131K
    7. 27729
    Prev
    Next
    INDEX
    Explanations

    correlations between variables

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

    The neuron spikes on terminology signalling statistical relationships—words like “between,” “association,” “correlation,” and similar markers of variables being linked.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Бил
    -1.15
     inimigo
    -1.14
     inimigos
    -1.12
     MiG
    -1.10
     herencia
    -1.10
    𝗁
    -1.09
     altavoz
    -1.09
    umesc
    -1.09
     τοῦ
    -1.07
     nombrado
    -1.06
    POSITIVE LOGITS
     each
    1.66
     all
    1.59
     both
    1.57
     overall
    1.55
     every
    1.43
     various
    1.28
     decreased
    1.25
     factors
    1.24
     increased
    1.22
     variables
    1.21
    Activations Density 0.073%

    No Known Activations