© 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. 9681
    Prev
    Next
    INDEX
    Explanations

    country domains

    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
    がない
    -1.50
     ekos
    -1.36
    が
    -1.28
    を見
    -1.24
    を
    -1.23
    態度
    -1.22
     vokal
    -1.21
    盉
    -1.21
     geografia
    -1.21
     alſo
    -1.21
    POSITIVE LOGITS
    うえ
    1.26
    ゼット
    1.17
    imanapun
    1.13
     wią
    1.11
    In
    1.10
    N
    1.09
     mandible
    1.06
    ありますか
    1.06
     will
    1.05
    onius
    1.05
    Activations Density 0.015%

    No Known Activations