© 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. 62714
    Prev
    Next
    INDEX
    Explanations

    beneath, behind, underneath

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    phonie
    -0.81
    附近
    -0.81
     mert
    -0.80
     특
    -0.79
    ">{
    -0.77
    hie
    -0.75
    لينكات
    -0.75
    FlowLayout
    -0.75
     verkle
    -0.75
     Ме
    -0.73
    POSITIVE LOGITS
     beneath
    4.75
     underneath
    4.13
     Beneath
    3.88
     behind
    3.86
    Beneath
    3.75
    behind
    3.02
    Behind
    2.92
     debajo
    2.83
     Behind
    2.80
    bene
    2.75
    Activations Density 0.071%

    No Known Activations