© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35640
    Prev
    Next
    INDEX
    Explanations

    individual, variability

    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_22/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
     sentada
    -1.00
     sentado
    -0.93
     अलावा
    -0.91
     menina
    -0.88
     complementary
    -0.88
     estranho
    -0.88
    分に
    -0.88
    ッシング
    -0.87
     criaturas
    -0.86
     velha
    -0.85
    POSITIVE LOGITS
    individual
    1.29
     individual
    1.28
    Individual
    1.27
     индивидуаль
    1.15
     variability
    1.13
    Each
    1.12
     Individual
    1.11
    個別
    1.06
     each
    1.05
     individuality
    1.04
    Activations Density 0.273%

    No Known Activations