© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10585
    Prev
    Next
    INDEX
    Explanations

    another or surprisingly

    np_acts-logits-general · gemini-2.5-flash-lite

    meaning and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     either
    0.52
     whereas
    0.49
     emphasises
    0.46
     असल्याने
    0.44
    vs
    0.44
     Whereas
    0.44
     emphasizes
    0.43
     Whatever
    0.43
     Either
    0.42
     any
    0.42
    POSITIVE LOGITS
     surprisingly
    0.83
     inesper
    0.77
     faktisk
    0.73
    実は
    0.70
    有一种
    0.70
    另一种
    0.68
     Surprisingly
    0.68
    有一個
    0.67
    Surprisingly
    0.66
     മറ്റൊരു
    0.66
    Activations Density 0.693%

    No Known Activations