© 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. 10-GEMMASCOPE-RES-131K
    7. 65109
    Prev
    Next
    INDEX
    Explanations

    Portuguese names and nationalities

    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
    h
    -2.25
     eyebrow
    -2.02
    ꯸
    -2.00
    就
    -1.98
     \
    -1.98
    y
    -1.95
     bzw
    -1.91
    '
    -1.87
     einigen
    -1.85
     apenas
    -1.84
    POSITIVE LOGITS
    er
    2.30
     moreno
    2.27
     It
    2.22
     všechny
    2.11
     salvador
    2.09
    ሯ
    2.02
     historische
    1.95
    世间
    1.95
    所说的
    1.93
     estratégico
    1.91
    Activations Density 0.004%

    No Known Activations