© 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. 106590
    Prev
    Next
    INDEX
    Explanations

    data following structure markers

    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
     much
    -0.81
     każdy
    -0.77
     even
    -0.77
     you
    -0.77
     getContent
    -0.73
    bitcoin
    -0.72
     expected
    -0.71
     many
    -0.70
     anyone
    -0.70
     comparable
    -0.69
    POSITIVE LOGITS
    versial
    0.85
    Yr
    0.85
     WOL
    0.83
    gota
    0.81
     MCC
    0.81
    vestimento
    0.80
    bluza
    0.80
     Testamento
    0.79
    tello
    0.78
    lapsing
    0.77
    Activations Density 0.001%

    No Known Activations