© 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. 71831
    Prev
    Next
    INDEX
    Explanations

    common components and imports

    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
     jeweiligen
    -1.48
     Entscheidungen
    -1.43
     こんな
    -1.42
     poszczegól
    -1.41
     verschillende
    -1.37
     gän
    -1.36
     eigentlichen
    -1.36
     erklär
    -1.35
     Bedürfn
    -1.34
     künf
    -1.33
    POSITIVE LOGITS
     even
    1.59
     حتی
    1.56
    컫
    1.49
     nawet
    1.48
     vaikka
    1.46
     même
    1.41
    elle
    1.41
    even
    1.40
     utro
    1.39
    
    1.39
    Activations Density 0.047%

    No Known Activations