© 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. 34-GEMMASCOPE-RES-131K
    7. 108185
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation

    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
    ‍
    -1.27
     over
    -0.82
     Pemerintah
    -0.80
     Direktur
    -0.80
     exquisite
    -0.78
    ＾＾；
    -0.77
     illiterate
    -0.75
    ucker
    -0.75
    ных
    -0.75
     Hingga
    -0.73
    POSITIVE LOGITS
    <b>
    1.83
    <i>
    1.34
    0.94
    </b>
    0.93
     weft
    0.84
    триму
    0.81
    </i>
    0.81
     Bé
    0.80
     stelt
    0.79
    
    0.79
    Activations Density 0.003%

    No Known Activations