© 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. 10-GEMMASCOPE-RES-131K
    7. 85311
    Prev
    Next
    INDEX
    Explanations

    TensorFlow graph visualization

    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_10/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
     pulizia
    -1.49
     condenado
    -1.48
     SqlParameter
    -1.41
    锷
    -1.39
     pictureBox
    -1.34
     ofici
    -1.34
     ilustracja
    -1.33
    罍
    -1.33
     procesu
    -1.33
    醱
    -1.32
    POSITIVE LOGITS
    </em>
    2.13
    </h4>
    1.42
    From
    1.41
    ,
    1.41
    </h2>
    1.37
     LOTS
    1.36
    .
    1.36
    </sup>
    1.34
    ↵↵
    1.29
     täglich
    1.26
    Activations Density 0.006%

    No Known Activations