© 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. 31221
    Prev
    Next
    INDEX
    Explanations

    patching or repair

    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
    ylase
    -0.89
    繇
    -0.88
     Prostate
    -0.84
     nadru
    -0.83
    tový
    -0.83
     angelegt
    -0.81
     ég
    -0.80
    fjspx
    -0.79
    Cancell
    -0.79
    天赋
    -0.77
    POSITIVE LOGITS
     repair
    3.41
     repairing
    2.64
     repairs
    2.59
    Repair
    2.53
     repaired
    2.52
     Repair
    2.50
    repair
    2.45
     patch
    2.44
     patching
    2.31
    patch
    2.22
    Activations Density 0.069%

    No Known Activations