© 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. 10-GEMMASCOPE-RES-131K
    7. 10067
    Prev
    Next
    INDEX
    Explanations

    civil rights and equality

    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
     Maybe
    -1.53
     that
    -1.51
     This
    -1.50
     There
    -1.44
     These
    -1.42
     Perhaps
    -1.41
    还不错
    -1.40
     možnosti
    -1.35
     Often
    -1.31
     They
    -1.28
    POSITIVE LOGITS
     abito
    1.67
     ulter
    1.59
     icona
    1.57
     dirit
    1.55
     deko
    1.54
     vne
    1.53
     sopr
    1.50
     maske
    1.48
     vna
    1.48
     geogra
    1.48
    Activations Density 0.026%

    No Known Activations