© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31352
    Prev
    Next
    INDEX
    Explanations

    Android ViewGroup, LayoutInflater

    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_34/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
    CreateMap
    -0.88
     LEVELS
    -0.80
     väg
    -0.79
     підприєм
    -0.77
    Regel
    -0.77
     vänner
    -0.77
    Τι
    -0.77
    watches
    -0.76
    Ingredi
    -0.76
     এবং
    -0.76
    POSITIVE LOGITS
    ViewGroup
    0.96
     niñas
    0.78
     moulding
    0.75
    dist
    0.73
    oté
    0.72
     cellspacing
    0.71
    자
    0.71
     キュ
    0.71
     discussion
    0.70
    深刻
    0.70
    Activations Density 0.004%

    No Known Activations