© 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. 119765
    Prev
    Next
    INDEX
    Explanations

    political movements and names

    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
     poë
    -1.52
    OTROS
    -1.50
    additional
    -1.48
     renforcé
    -1.48
     miljö
    -1.46
     günü
    -1.45
     食物
    -1.45
    Approximately
    -1.45
    BIBLIO
    -1.44
     régal
    -1.44
    POSITIVE LOGITS
     like
    1.80
     all
    1.75
     as
    1.64
     and
    1.57
     despite
    1.48
    教材
    1.41
    匾
    1.37
    šené
    1.36
     not
    1.34
     old
    1.32
    Activations Density 0.080%

    No Known Activations