© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11838
    Prev
    Next
    INDEX
    Explanations

    versatile, multi-purpose, all-in-one

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

    general and versatile

    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
    itories
    0.37
    iffs
    0.37
    னிய
    0.37
    pytest
    0.37
    Fechar
    0.36
    🤵
    0.36
    дії
    0.36
    昭
    0.35
    佷
    0.35
     मिलकर
    0.35
    POSITIVE LOGITS
     multipurpose
    2.16
     versatile
    2.13
     versatility
    1.95
     multifunctional
    1.84
     универса
    1.73
     multifunction
    1.72
     multifaceted
    1.49
    multif
    1.44
     Multif
    1.41
    汎
    1.37
    Activations Density 0.671%

    No Known Activations