© 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. 99650
    Prev
    Next
    INDEX
    Explanations

    insoluble / individualized / unresolved

    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
    }
    -3.38
    </i>
    -3.27
     "
    -3.11
    -
    -3.06
    ]
    -3.03
    [
    -2.39
    {
    -2.31
    u
    -2.25
    ....
    -2.09
     turbulent
    -2.09
    POSITIVE LOGITS
    淠
    2.89
    
    2.58
    酲
    2.55
    脔
    2.48
    蛱
    2.48
    
    2.48
     corazon
    2.41
    萑
    2.36
    havior
    2.36
    鲧
    2.34
    Activations Density 0.005%

    No Known Activations