© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    originally

    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
    l
    0.43
    )$
    0.41
    π
    0.37
     detects
    0.36
    o
    0.36
    在使用
    0.35
    )
    0.35
    ι
    0.35
     summarizes
    0.35
    adata
    0.35
    POSITIVE LOGITS
     ursprüng
    0.75
     originalmente
    0.74
     ursprünglich
    0.70
    Originally
    0.68
     habíamos
    0.64
     изначально
    0.64
    当初
    0.62
    originally
    0.61
     originally
    0.61
     Originally
    0.59
    Activations Density 0.440%

    No Known Activations