© 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. 63397
    Prev
    Next
    INDEX
    Explanations

    using System; namespace

    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
     باتری
    -0.94
    はいけない
    -0.82
     khỏi
    -0.80
    Herzliche
    -0.79
     supprim
    -0.79
     zcela
    -0.78
    astery
    -0.77
    ReadLine
    -0.77
    migrationBuilder
    -0.77
    Emmanuel
    -0.77
    POSITIVE LOGITS
     arrayList
    0.87
    omato
    0.82
     Bildungs
    0.81
     approbation
    0.79
     左
    0.79
     geh
    0.79
     dicembre
    0.78
     '"+
    0.77
     suoi
    0.77
     collections
    0.77
    Activations Density 0.021%

    No Known Activations