© 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. 31902
    Prev
    Next
    INDEX
    Explanations

    software licensing and code structures

    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
    National
    -0.82
     قطر
    -0.82
     oraciones
    -0.81
    GF
    -0.81
    belts
    -0.80
     Тут
    -0.80
     Scissors
    -0.80
     刺繍
    -0.77
    setCenter
    -0.76
     Kingfisher
    -0.76
    POSITIVE LOGITS
     ladies
    0.81
     tank
    0.80
    上次
    0.79
     incur
    0.76
     НИ
    0.74
     mú
    0.71
     hoes
    0.71
    Examen
    0.71
    atorias
    0.71
    Tanks
    0.71
    Activations Density 0.006%

    No Known Activations