© 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. 10100
    Prev
    Next
    INDEX
    Explanations

    first

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

    first, second, last entities

    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
     오랜
    0.46
     vidas
    0.46
    Skippable
    0.41
     vire
    0.40
    uparavant
    0.40
     veille
    0.40
     ちょっと
    0.40
    伙
    0.39
     мотива
    0.39
     weak
    0.39
    POSITIVE LOGITS
     полностью
    0.53
     openly
    0.51
     সম্পূর্ন
    0.49
     పూర్తి
    0.49
     সম্পূর্ণরূপে
    0.48
     পুরোপুরি
    0.48
     να
    0.48
     volledig
    0.47
     официально
    0.47
     fully
    0.46
    Activations Density 0.167%

    No Known Activations