© 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. 53-GEMMASCOPE-2-RES-65K
    7. 6189
    Prev
    Next
    INDEX
    Explanations

    general summary

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

    technical terms

    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_53_width_65k_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
    ത്തിന്റെയും
    0.41
    োপাধ
    0.38
    ുമ്പോൾ
    0.37
    ៕
    0.37
    ).\\
    0.36
     mediante
    0.35
    𝓟
    0.35
    鹂
    0.35
    .}~\
    0.35
    മാക്കി
    0.34
    POSITIVE LOGITS
     There
    0.86
     Although
    0.84
     However
    0.80
     しかし
    0.77
     Также
    0.75
     Beberapa
    0.73
     When
    0.73
     Therefore
    0.71
     Unfortunately
    0.71
     Additionally
    0.70
    Activations Density 0.569%

    No Known Activations