© 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. 10-GEMMASCOPE-RES-131K
    7. 112141
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions before nouns

    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
     both
    -1.55
    %;
    -1.55
    ныя
    -1.55
     dataSnapshot
    -1.52
     palme
    -1.39
     will
    -1.37
    ];
    -1.36
     Ausführungen
    -1.34
     Allegretto
    -1.34
     Apertura
    -1.34
    POSITIVE LOGITS
     the
    1.68
     it
    1.62
     utilizó
    1.34
     bedient
    1.30
     -
    1.30
     mismos
    1.27
    mereka
    1.27
    陷入
    1.26
     mohl
    1.26
    なのは
    1.23
    Activations Density 0.140%

    No Known Activations