© 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. 77547
    Prev
    Next
    INDEX
    Explanations

    learning curve

    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
    ện
    -0.90
     グラン
    -0.79
    ванні
    -0.79
     meren
    -0.77
    рс
    -0.74
    íž
    -0.73
     tempel
    -0.73
    циаль
    -0.72
     malen
    -0.72
     kän
    -0.72
    POSITIVE LOGITS
     learning
    5.72
    learning
    4.47
     Learning
    4.22
    Learning
    4.00
     LEARNING
    3.56
     learn
    3.47
    学习
    3.25
     aprender
    3.20
    LEARNING
    3.19
     steep
    3.08
    Activations Density 0.046%

    No Known Activations