© 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. 2634
    Prev
    Next
    INDEX
    Explanations

    questions starting with does

    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
     інші
    -1.41
     них
    -1.16
     cuando
    -1.10
     berbagai
    -1.09
    tists
    -1.09
     zahlreichen
    -1.07
    iked
    -1.04
     ними
    -1.04
    便利です
    -1.02
    鬟
    -1.02
    POSITIVE LOGITS
     it
    1.97
     this
    1.75
     your
    1.62
     anyone
    1.55
     anybody
    1.47
     that
    1.13
     each
    1.12
     seem
    1.09
     everyone
    1.08
     someone
    1.02
    Activations Density 0.023%

    No Known Activations