© 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. 41692
    Prev
    Next
    INDEX
    Explanations

    words starting with "Sie"

    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
    ↵↵
    -3.09
    H
    -3.06
    ↵
    -2.80
    K
    -2.48
    S
    -2.45
    </em>
    -2.42
     earliest
    -2.42
     excite
    -2.31
     eloquent
    -2.30
    籀
    -2.30
    POSITIVE LOGITS
     This
    2.97
    
    2.91
    颪
    2.66
    皤
    2.55
    }$
    2.55
     این
    2.47
     اشار
    2.45
    ㌘
    2.44
     rajut
    2.44
     menyen
    2.44
    Activations Density 0.005%

    No Known Activations