© 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. 249
    Prev
    Next
    INDEX
    Explanations

    alone

    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
    >
    -2.86
    </i>
    -2.67
     is
    -2.50
    -2.39
    ^{
    -2.27
    蹰
    -2.25
     to
    -2.23
    <td>
    -2.19
     необходимо
    -2.19
     bizarre
    -2.11
    POSITIVE LOGITS
    龶
    2.23
    
    2.16
    玏
    2.11
     fashioned
    1.99
     diminish
    1.98
    ization
    1.98
    AutoresizingMask
    1.97
    ;/
    1.95
    翾
    1.94
    
    1.94
    Activations Density 0.004%

    No Known Activations