© 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. 34-GEMMASCOPE-RES-131K
    7. 108675
    Prev
    Next
    INDEX
    Explanations

    find the value

    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
    Лі
    -0.88
     auxiliar
    -0.84
    Pozdrawiam
    -0.84
     lapis
    -0.83
     flamen
    -0.83
     quicker
    -0.82
    живать
    -0.81
     custos
    -0.81
     inova
    -0.80
     Moisés
    -0.80
    POSITIVE LOGITS
     чтобы
    1.27
    使得
    1.02
     để
    0.94
     smallest
    0.93
    ansa
    0.93
     that
    0.88
     knowing
    0.88
    PHeader
    0.88
    Knowing
    0.88
     που
    0.86
    Activations Density 0.069%

    No Known Activations