© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107745
    Prev
    Next
    INDEX
    Explanations

    Portuguese and French words

    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_34/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
     vejo
    -0.93
     minY
    -0.89
    罰
    -0.85
     ________
    -0.84
     een
    -0.84
    精确
    -0.83
     mucho
    -0.82
    appliquent
    -0.81
    なんと
    -0.81
     now
    -0.81
    POSITIVE LOGITS
     também
    1.02
    onore
    0.99
     strati
    0.96
    stva
    0.93
    ⅗
    0.93
    graphique
    0.93
     nommée
    0.92
    ところに
    0.92
     défaut
    0.91
    blico
    0.91
    Activations Density 0.021%

    No Known Activations