© 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. 59206
    Prev
    Next
    INDEX
    Explanations

    foremost / CompilerGenerated

    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
    </i>
    -3.52
     {
    -2.92
     
    -2.88
    &
    -2.88
    {
    -2.75
    <i>
    -2.63
    <
    -2.53
    }
    -2.41
    -
    -2.38
     *
    -2.36
    POSITIVE LOGITS
     哪
    2.89
    ?”
    2.78
    傒
    2.41
    蒹
    2.39
    卨
    2.39
    ſſer
    2.39
    嚶
    2.39
    
    2.39
    몀
    2.39
     și
    2.38
    Activations Density 0.001%

    No Known Activations