© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1826
    Prev
    Next
    INDEX
    Explanations

    dense retrieval

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᕕ
    0.43
     изображение
    0.41
    ');//
    0.41
    Sunrise
    0.41
    ]::
    0.40
    Tabpage
    0.40
    [,,"
    0.40
    ഞ്ഞ
    0.40
    <?
    0.40
    曈
    0.40
    POSITIVE LOGITS
     langchain
    1.07
     embeddings
    0.75
     LL
    0.71
     OpenAI
    0.70
     QA
    0.69
     retriever
    0.69
     document
    0.68
     doc
    0.68
     chatbot
    0.68
     chatbots
    0.67
    Activations Density 0.647%

    No Known Activations