© 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. 1355
    Prev
    Next
    INDEX
    Explanations

    disintegration of matter

    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
    );
    
    -3.20
     to
    -2.97
    )
    
    -2.66
    $
    
    -2.61
    渽
    -2.59
    ):
    
    -2.50
     naszego
    -2.45
    鼍
    -2.42
     durchgeführt
    -2.41
    ']
    
    -2.34
    POSITIVE LOGITS
    t
    2.42
    琹
    2.31
    have
    2.11
     embrace
    2.09
    壜
    2.08
     disposent
    2.08
    dzić
    2.06
    焿
    2.06
    izielle
    2.05
     selben
    2.05
    Activations Density 0.001%

    No Known Activations