© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124003
    Prev
    Next
    INDEX
    Explanations

    city names followed by em dash

    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
    '
    -2.83
     acoged
    -2.02
    </h4>
    -1.92
    鱷
    -1.88
    了许多
    -1.88
     '
    -1.84
    </strong>
    -1.83
     这个
    -1.82
     '-
    -1.80
     ilustraciones
    -1.78
    POSITIVE LOGITS
    ቍ
    2.25
    ଞ
    2.14
    ”،
    2.02
     zis
    2.00
    archiwizowane
    1.97
    geſ
    1.96
    咴
    1.96
    </i>
    1.96
    
    1.94
    沇
    1.93
    Activations Density 0.010%

    No Known Activations