© 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. 118875
    Prev
    Next
    INDEX
    Explanations

    words ending in ded

    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
    ឵
    -2.63
    閙
    -2.34
    owment
    -2.33
    翃
    -2.33
    褔
    -2.30
    ⬯
    -2.25
    とその
    -2.23
    
    -2.17
    会导致
    -2.17
     horarios
    -2.17
    POSITIVE LOGITS
    ded
    3.72
    },
    2.80
    —
    2.58
    0
    2.58
    an
    2.30
    我们
    2.27
    We
    2.22
     anún
    2.22
     Теперь
    2.19
    y
    2.19
    Activations Density 0.005%

    No Known Activations