© 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. 22-GEMMASCOPE-RES-131K
    7. 129947
    Prev
    Next
    INDEX
    Explanations

    list items files directories

    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
    憷
    -1.00
     tunik
    -1.00
     jabón
    -0.98
     dormitorios
    -0.97
    danh
    -0.96
     karet
    -0.94
     cepillo
    -0.93
    jordan
    -0.93
     bailarina
    -0.93
    phalt
    -0.93
    POSITIVE LOGITS
     adventurous
    0.95
     فيها
    0.93
    での
    0.93
    ншот
    0.93
     #
    0.82
     may
    0.82
    そのため
    0.81
    辅导
    0.81
     conglomer
    0.81
     Também
    0.81
    Activations Density 0.032%

    No Known Activations