© 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. 15314
    Prev
    Next
    INDEX
    Explanations

    transition words

    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
     and
    -1.46
     didn
    -1.18
    Tapi
    -1.08
    Karakteristik
    -1.05
    炀
    -1.03
      
    -1.02
    vejec
    -1.00
    のお話
    -0.99
    türk
    -0.98
     đảm
    -0.96
    POSITIVE LOGITS
    ！！”
    1.13
    ścioła
    1.04
    ！！！”
    0.98
    独特
    0.97
     actuels
    0.96
    eabouts
    0.95
    ,'
    0.95
     людини
    0.94
    Aiheesta
    0.93
    几年
    0.93
    Activations Density 0.033%

    No Known Activations