© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69658
    Prev
    Next
    INDEX
    Explanations

    trouble requesting

    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
     and
    -1.52
     και
    -1.30
      
    -1.29
    에
    -1.24
    ,
    -1.23
     и
    -1.20
     Nach
    -1.20
     son
    -1.20
     '+':
    -1.18
     escuchado
    -1.18
    POSITIVE LOGITS
    袛
    1.46
     handful
    1.38
     کردیم
    1.34
    旒
    1.30
    们的
    1.29
    檍
    1.29
    接下來
    1.28
     farfetch
    1.25
     manj
    1.24
    versial
    1.21
    Activations Density 0.013%

    No Known Activations