© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77869
    Prev
    Next
    INDEX
    Explanations

    important updates and edits

    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
     our
    -0.93
     Began
    -0.82
     kombiniert
    -0.78
    %,
    -0.78
    ૧
    -0.77
     रो
    -0.75
     Efq
    -0.73
     baffle
    -0.73
     Nucle
    -0.72
     abol
    -0.72
    POSITIVE LOGITS
     update
    4.81
    UPDATE
    4.56
     UPDATE
    4.50
     Update
    4.13
    Update
    4.06
    update
    4.03
     edit
    3.92
    EDIT
    3.81
     EDIT
    3.61
    Edit
    3.56
    Activations Density 0.093%

    No Known Activations