© 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. 10-GEMMASCOPE-RES-131K
    7. 13084
    Prev
    Next
    INDEX
    Explanations

    religious denominations and institutions

    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
    What
    -1.86
    谙
    -1.56
    Who
    -1.51
     to
    -1.48
    How
    -1.44
    𝑌
    -1.42
    Also
    -1.41
    Another
    -1.38
    Your
    -1.38
                            
    -1.38
    POSITIVE LOGITS
     sababu
    1.34
    などが
    1.30
     volleyball
    1.23
    的身体
    1.23
    的血
    1.21
     apel
    1.21
     maïs
    1.18
    Wins
    1.17
    はこんな感じ
    1.17
    ças
    1.16
    Activations Density 0.030%

    No Known Activations