© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101219
    Prev
    Next
    INDEX
    Explanations

    fluid drainage or electrical source/drain

    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
    킁
    -2.81
    篥
    -2.66
    缡
    -2.42
    釹
    -2.33
    
    -2.33
    盌
    -2.30
     Seriously
    -2.28
     désolés
    -2.28
     Which
    -2.27
    al
    -2.23
    POSITIVE LOGITS
    ),
    2.42
    sibilité
    2.41
    }
    2.31
     komplette
    2.25
     luxuri
    2.22
    ?
    2.19
     वह
    2.16
    ଃ
    2.16
     observer
    2.14
    驀
    2.13
    Activations Density 0.004%

    No Known Activations