© 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. 73115
    Prev
    Next
    INDEX
    Explanations

    sentences following punctuation

    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
     précédentes
    -0.94
    特别是
    -0.93
    Terra
    -0.89
    𝑰
    -0.84
     régionales
    -0.84
    敌人
    -0.83
     femininos
    -0.82
     ficción
    -0.82
    ◦
    -0.82
    Pon
    -0.82
    POSITIVE LOGITS
     gelukkig
    1.04
     but
    1.02
     intervention
    0.95
     Fortunately
    0.93
    好在
    0.90
    Fortunately
    0.90
     luckily
    0.90
     then
    0.89
    AÇÃO
    0.86
     fortunately
    0.86
    Activations Density 0.027%

    No Known Activations