© 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. 129873
    Prev
    Next
    INDEX
    Explanations

    plural demonstrative pronoun

    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
     "
    -2.09
    —
    -1.96
     zarówno
    -1.91
     entram
    -1.76
     
    -1.62
     forment
    -1.62
     politi
    -1.57
     turmoil
    -1.51
     anul
    -1.48
     他
    -1.48
    POSITIVE LOGITS
     themselves
    2.09
     actuaciones
    2.02
     које
    1.96
     promesas
    1.89
     också
    1.88
     eivät
    1.88
    خدا
    1.78
     вже
    1.73
     princesas
    1.72
     avulla
    1.71
    Activations Density 0.074%

    No Known Activations