© 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. 34-GEMMASCOPE-RES-131K
    7. 54150
    Prev
    Next
    INDEX
    Explanations

    deal in, referred to, Asst

    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
     terk
    -0.79
    観音
    -0.73
     captura
    -0.69
     Хе
    -0.66
     pore
    -0.65
     marca
    -0.64
    точно
    -0.63
     الفي
    -0.63
     employé
    -0.63
     vtk
    -0.63
    POSITIVE LOGITS
     guessed
    0.78
    ριά
    0.77
    丸
    0.71
    UVWXYZ
    0.69
     Aristi
    0.67
    threaded
    0.65
     épreuves
    0.65
    ôm
    0.65
     Jaya
    0.65
    segs
    0.65
    Activations Density 0.050%

    No Known Activations