© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64480
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and dimensionality reduction

    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
    wati
    -0.71
    bró
    -0.71
    onsumsi
    -0.71
    듦
    -0.70
     votar
    -0.70
    ftances
    -0.70
    Spear
    -0.68
    fachada
    -0.68
    isenberg
    -0.68
    あっ
    -0.67
    POSITIVE LOGITS
     analysis
    1.61
     Analysis
    1.56
    Analysis
    1.48
    analysis
    1.38
    分析
    1.37
     ANALYSIS
    1.20
     discriminant
    1.15
    discrimin
    1.14
     análisis
    1.13
     discrimin
    1.12
    Activations Density 0.030%

    No Known Activations