© 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. 128090
    Prev
    Next
    INDEX
    Explanations

    would be great if

    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
    despite
    -1.88
    ᚔ
    -1.82
     condicionado
    -1.78
     quatrième
    -1.74
    籏
    -1.69
    𖤣
    -1.68
    mination
    -1.67
     cinquième
    -1.67
    excellent
    -1.66
     primeiros
    -1.66
    POSITIVE LOGITS
     for
    2.25
    {
    1.77
     if
    1.73
     would
    1.57
     Since
    1.55
    “
    1.49
    этому
    1.48
     Needed
    1.44
    人都
    1.42
    =
    1.41
    Activations Density 0.016%

    No Known Activations