© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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
     regalías
    -1.77
     that
    -1.71
     exportaciones
    -1.67
     erfolgreich
    -1.63
     persönlich
    -1.59
     joyas
    -1.59
     Unterrichts
    -1.59
     auswählen
    -1.59
     lebte
    -1.58
    
    -1.57
    POSITIVE LOGITS
    The
    1.77
     tages
    1.46
    SEGU
    1.45
     слегка
    1.41
     variante
    1.40
    Siempre
    1.39
    亲爱的
    1.35
    私たちは
    1.34
    bie
    1.32
    我們
    1.31
    Activations Density 0.007%

    No Known Activations