© 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. 34-GEMMASCOPE-RES-131K
    7. 106888
    Prev
    Next
    INDEX
    Explanations

    closing parentheses after abbreviations

    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
     și
    -0.90
    曠
    -0.89
     और
    -0.89
     usually
    -0.84
    and
    -0.84
    +</
    -0.82
     marginLeft
    -0.82
     марта
    -0.81
     divorce
    -0.79
     great
    -0.78
    POSITIVE LOGITS
     WHEREAS
    0.94
     germin
    0.88
    GOLF
    0.88
     facili
    0.88
     Ls
    0.86
     fuc
    0.85
     SOB
    0.84
     stater
    0.83
    Zor
    0.82
     epo
    0.82
    Activations Density 0.093%

    No Known Activations