© 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. 11526
    Prev
    Next
    INDEX
    Explanations

    Montana and Colombia

    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
    馓
    -2.94
    
    -2.83
    饪
    -2.73
     againſt
    -2.72
    ться
    -2.69
    𞤢
    -2.67
     This
    -2.67
     dovuto
    -2.64
     Efek
    -2.58
    躂
    -2.56
    POSITIVE LOGITS
    i
    2.73
     In
    2.67
    ↵
    2.66
    </b>
    2.34
    .
    2.31
     tetapi
    2.27
    Y
    2.27
    ワ
    2.17
     December
    2.17
     vaguely
    2.11
    Activations Density 0.003%

    No Known Activations