© 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. 48708
    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
     goes
    -0.90
     Going
    -0.85
    ctron
    -0.85
     generally
    -0.82
     D
    -0.78
     people
    -0.78
     investasi
    -0.77
     large
    -0.77
     big
    -0.75
     seven
    -0.75
    POSITIVE LOGITS
    usive
    0.89
     interrom
    0.87
     exklu
    0.84
     VY
    0.84
    ='$
    0.82
    COMO
    0.81
    胭
    0.81
    rieron
    0.80
     WISH
    0.79
     répon
    0.79
    Activations Density 0.004%

    No Known Activations