© 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. 10290
    Prev
    Next
    INDEX
    Explanations

    Care Home

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

    Esperanto, scientific terms, brands, names

    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
    ₱
    0.42
    សូម
    0.42
     Agregar
    0.41
    ຕໍ່
    0.40
    “)
    0.40
    좀
    0.39
    ستی
    0.38
    <unused454>
    0.38
     बीते
    0.37
    Eventually
    0.37
    POSITIVE LOGITS
     brauchen
    0.44
     skup
    0.38
     braucht
    0.37
     sabem
    0.37
     kaun
    0.37
    
    0.36
     `.
    0.35
    ताच
    0.35
     नाहीत
    0.35
    ﻛ
    0.35
    Activations Density 0.383%

    No Known Activations