© 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. 116313
    Prev
    Next
    INDEX
    Explanations

    Indian actors and copyright notices

    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
     accused
    -0.97
    Auburn
    -0.80
     Auburn
    -0.73
    urés
    -0.73
     kir
    -0.72
     формате
    -0.71
     Bowie
    -0.71
    Exodus
    -0.70
     Už
    -0.69
     bleue
    -0.69
    POSITIVE LOGITS
     Dharma
    1.05
    ulia
    0.78
     Alia
    0.77
     Karan
    0.75
     LoL
    0.75
     Motta
    0.74
    multip
    0.72
     SOT
    0.71
     Corner
    0.70
    submissions
    0.69
    Activations Density 0.008%

    No Known Activations