© 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. 99131
    Prev
    Next
    INDEX
    Explanations

    President followed by name

    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
     in
    -2.48
    ."
    -1.95
    ,"
    -1.57
    ⼈
    -1.53
     a
    -1.46
    {?>
    -1.45
    !"
    -1.44
    眩
    -1.44
    ！！”
    -1.44
    atação
    -1.41
    POSITIVE LOGITS
     aspetta
    1.69
     två
    1.55
     vuole
    1.55
     abband
    1.46
     potrà
    1.45
    儅
    1.45
     manquer
    1.44
     farà
    1.44
     effettu
    1.44
     sarebbe
    1.44
    Activations Density 0.025%

    No Known Activations