© 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. 68104
    Prev
    Next
    INDEX
    Explanations

    questions and conditions

    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
     kerusakan
    -1.19
     of
    -1.14
    GRAFÍA
    -1.02
     kini
    -1.00
     unserem
    -1.00
     primera
    -0.97
     Beschreibung
    -0.97
    〜。
    -0.94
     sehr
    -0.93
    taya
    -0.93
    POSITIVE LOGITS
     you
    1.30
     např
    1.28
     competición
    1.14
    ALTY
    1.13
     Ofrece
    1.12
     Lleva
    1.12
     Obtén
    1.11
     distinta
    1.11
    hopped
    1.09
     your
    1.04
    Activations Density 0.022%

    No Known Activations