© 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. 30612
    Prev
    Next
    INDEX
    Explanations

    Compile, remove, or code

    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
     butterknife
    -0.79
    fass
    -0.75
     бед
    -0.74
     diss
    -0.73
    లా
    -0.73
    npmjs
    -0.70
     Le
    -0.69
    enein
    -0.69
     velas
    -0.69
     Gruppe
    -0.69
    POSITIVE LOGITS
     phylogenetic
    0.86
     espesor
    0.84
     tyrant
    0.81
     Invis
    0.79
     kpop
    0.79
    exporter
    0.78
     anbieten
    0.77
    婚
    0.77
     länger
    0.77
    其实
    0.77
    Activations Density 0.000%

    No Known Activations