© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21375
    Prev
    Next
    INDEX
    Explanations

    system configuration identifiers

    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
     både
    -1.63
     both
    -1.51
     also
    -1.37
      
    -1.35
    es
    -1.34
     either
    -1.33
     nació
    -1.28
     each
    -1.25
     quí
    -1.24
     alike
    -1.21
    POSITIVE LOGITS
    ()]);
    1.52
     Algorithm
    1.46
    しくは
    1.38
     Periodic
    1.36
     όταν
    1.34
     ヶ
    1.34
     εφ
    1.34
    𝗻
    1.30
     هناك
    1.28
     Scheduled
    1.28
    Activations Density 0.024%

    No Known Activations