© 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. 60084
    Prev
    Next
    INDEX
    Explanations

    on track or corrected

    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
     to
    -1.46
     solidaridad
    -1.35
    很赞
    -1.25
     única
    -1.20
     conoce
    -1.20
    icolor
    -1.17
     esconder
    -1.16
     ganó
    -1.16
    oceros
    -1.15
     MUCH
    -1.14
    POSITIVE LOGITS
    also
    1.30
    posições
    1.27
     posteriori
    1.27
    鉕
    1.27
     vå
    1.21
     Príncipe
    1.21
     різ
    1.20
    搭配
    1.20
    Composição
    1.20
      “
    1.13
    Activations Density 0.077%

    No Known Activations