© 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. 22-GEMMASCOPE-RES-131K
    7. 15317
    Prev
    Next
    INDEX
    Explanations

    configureSupplementaryView

    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_22/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
     rilass
    -1.20
     merav
    -1.13
    𖣘
    -1.05
    plantas
    -1.04
     atasan
    -0.98
    alimentos
    -0.98
     erfü
    -0.98
     contatto
    -0.97
     riscal
    -0.97
    囑
    -0.97
    POSITIVE LOGITS
    suo
    0.94
    minY
    0.90
    клы
    0.86
    CAPE
    0.84
     to
    0.82
    VEGF
    0.82
    etype
    0.81
    ylabel
    0.81
     dollar
    0.81
     élite
    0.81
    Activations Density 0.040%

    No Known Activations