© 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. 22-GEMMASCOPE-RES-131K
    7. 54480
    Prev
    Next
    INDEX
    Explanations

    Posts Tagged/Archives

    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_22/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
     blusa
    -1.47
     esponja
    -1.16
     motocicleta
    -1.13
     garrafa
    -1.12
     estufa
    -1.10
    defaultProps
    -1.08
     transmite
    -1.08
    elsif
    -1.08
    lentes
    -1.06
     camiseta
    -1.05
    POSITIVE LOGITS
    strated
    1.15
    engarkan
    1.10
    ʹ
    1.09
     ссылке
    1.03
     (*(
    0.99
    嗪
    0.94
     astfel
    0.94
    utu
    0.94
    ambassade
    0.94
     instead
    0.93
    Activations Density 0.000%

    No Known Activations