© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62752
    Prev
    Next
    INDEX
    Explanations

    mix and equations

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

    The neuron fires strongly on common multiword prepositional phrases that introduce a noun phrase—especially sequences like “in the,” “to the,” “out of the,” “into the,” 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_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
     pozo
    -0.83
    再多
    -0.80
    他有
    -0.80
     gestes
    -0.80
     både
    -0.80
     carattere
    -0.76
     لأن
    -0.75
     différentes
    -0.75
    Yep
    -0.75
     riduzione
    -0.74
    POSITIVE LOGITS
     equation
    5.03
    equation
    3.50
     Equation
    3.36
     equations
    3.33
    Equation
    3.11
     mix
    2.94
     picture
    2.81
    equations
    2.53
     Equations
    2.52
    Equations
    2.42
    Activations Density 0.041%

    No Known Activations