© 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. 47746
    Prev
    Next
    INDEX
    Explanations

    names followed by "by"

    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
     departament
    -0.79
     created
    -0.76
    inę
    -0.75
    assorted
    -0.75
     bhai
    -0.74
     aussitôt
    -0.73
     Morav
    -0.73
    banding
    -0.72
     sayang
    -0.72
     kuda
    -0.72
    POSITIVE LOGITS
    Contact
    2.59
     contact
    2.52
     Contact
    2.38
    contact
    2.09
     CONTACT
    1.95
    CONTACT
    1.88
    Reach
    1.86
    Email
    1.55
     contacting
    1.48
    email
    1.46
    Activations Density 0.027%

    No Known Activations