© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11474
    Prev
    Next
    INDEX
    Explanations

    majority stake

    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_31_width_16k_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
    )
    0.48
     formulated
    0.48
    nal
    0.47
                
    0.46
    im
    0.46
    na
    0.45
     empty
    0.45
    sim
    0.45
    2
    0.44
    3
    0.44
    POSITIVE LOGITS
     recibirá
    0.52
    ະພັນ
    0.52
     conversación
    0.49
    REACTOR
    0.49
     poderá
    0.49
     recibe
    0.49
    दस्त
    0.48
    збеки
    0.48
    ச்சத்து
    0.47
     reciben
    0.47
    Activations Density 0.028%

    No Known Activations