© 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. 21960
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
     as
    -1.90
     уже
    -1.56
    We
    -1.56
     bereits
    -1.53
     or
    -1.48
     where
    -1.44
     we
    -1.41
    ↵
    -1.41
     Если
    -1.37
    𝘬
    -1.36
    POSITIVE LOGITS
    mostly
    1.55
     dětí
    1.52
    idk
    1.52
    AdvEx
    1.49
     kalender
    1.49
     Qaeda
    1.48
     kela
    1.47
    sont
    1.46
     kien
    1.46
    mainly
    1.46
    Activations Density 0.114%

    No Known Activations