© 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. 10-GEMMASCOPE-RES-131K
    7. 73310
    Prev
    Next
    INDEX
    Explanations

    separators and code formatting

    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_10/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
    </h2>
    -1.96
    .
    -1.90
     or
    -1.76
     is
    -1.70
     at
    -1.62
     їх
    -1.62
    Fußball
    -1.60
     і
    -1.56
     panas
    -1.55
     剑
    -1.52
    POSITIVE LOGITS
     the
    1.91
     wahre
    1.74
     further
    1.62
    旁边的
    1.62
    od
    1.57
     vastly
    1.55
    嵓
    1.52
    ;(
    1.49
     admired
    1.48
     separate
    1.48
    Activations Density 0.005%

    No Known Activations