© 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. 111168
    Prev
    Next
    INDEX
    Explanations

    occurrence of events

    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
     to
    -1.89
     nowej
    -1.52
     IBRARY
    -1.48
     during
    -1.35
     कैसी
    -1.33
    
    -1.33
     Psico
    -1.30
     nuevos
    -1.28
    pagnes
    -1.28
     新
    -1.27
    POSITIVE LOGITS
     was
    1.41
    夘
    1.39
    правка
    1.37
     elástico
    1.29
    AILABILITY
    1.28
     cinturón
    1.26
     graveyard
    1.25
     ögon
    1.24
     unteren
    1.23
    ).
    1.22
    Activations Density 0.029%

    No Known Activations