© 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. 1263
    Prev
    Next
    INDEX
    Explanations

    mathematical comparisons and operations

    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
     谢
    0.37
     হাড়
    0.37
     terroir
    0.34
     അവര്‍
    0.33
     هغه
    0.33
     اٹھ
    0.33
    𝑵
    0.33
     полного
    0.33
     ними
    0.33
     সি
    0.32
    POSITIVE LOGITS
    .
    0.39
    ٫
    0.36
    だと
    0.35
    hey
    0.35
     monotonically
    0.35
     represented
    0.34
     corresponds
    0.34
    :
    0.34
     nant
    0.33
     demonstrates
    0.33
    Activations Density 0.587%

    No Known Activations