© 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. 34-GEMMASCOPE-RES-131K
    7. 116854
    Prev
    Next
    INDEX
    Explanations

    western media and America

    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
     pengar
    -1.27
     continually
    -1.26
     focuses
    -1.21
     Ministero
    -1.21
     maniere
    -1.20
     entraî
    -1.19
     eduk
    -1.17
     THROUGH
    -1.16
     DURING
    -1.16
     teo
    -1.16
    POSITIVE LOGITS
     or
    1.53
     unusually
    1.29
     and
    1.28
     without
    1.27
     for
    1.20
     by
    1.18
     two
    1.14
     superbly
    1.13
     profoundly
    1.13
     four
    1.12
    Activations Density 0.039%

    No Known Activations