© 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. 22-GEMMASCOPE-RES-131K
    7. 84363
    Prev
    Next
    INDEX
    Explanations

    more than

    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_22/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
     caucho
    -1.15
     behoort
    -1.13
     samenwerking
    -1.13
     apropiado
    -1.12
     tijden
    -1.11
     virksom
    -1.11
     vinilo
    -1.11
    indonesia
    -1.09
     vrienden
    -1.09
     følgende
    -1.09
    POSITIVE LOGITS
     just
    2.38
     просто
    2.31
     merely
    2.14
     simply
    2.14
     mere
    2.05
    แค่
    1.87
    只是
    1.69
     مجرد
    1.68
    ただ
    1.59
    เพียง
    1.55
    Activations Density 0.017%

    No Known Activations