© 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. 40097
    Prev
    Next
    INDEX
    Explanations

    URLs with common beginnings

    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
     ordinateur
    -1.84
    <0xE0>
    -1.77
    orist
    -1.66
     POLLUTION
    -1.61
    skich
    -1.57
    rfan
    -1.51
     secours
    -1.49
    🦐
    -1.49
     trône
    -1.48
    Río
    -1.48
    POSITIVE LOGITS
     of
    1.94
    ↵↵
    1.90
     (
    1.58
     about
    1.56
    </h2>
    1.53
    ↵
    1.49
     and
    1.45
     created
    1.40
     требует
    1.33
     which
    1.31
    Activations Density 0.025%

    No Known Activations