© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47466
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     angled
    -0.86
     algodão
    -0.84
    UserDetails
    -0.75
     Steuern
    -0.73
    岁月
    -0.72
     uneasy
    -0.72
     étanche
    -0.72
    虏
    -0.71
     cervical
    -0.71
    Alpes
    -0.70
    POSITIVE LOGITS
     pemain
    0.80
    術
    0.75
     SDC
    0.74
     Bial
    0.71
     Expan
    0.71
     ransom
    0.71
    hemi
    0.70
     消
    0.69
     getMessage
    0.68
    ▋
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.