© 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-262K
    7. 25767
    Prev
    Next
    INDEX
    Explanations

    spherical Earth

    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_262k_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
    ꞎ
    0.45
    것도
    0.42
     adicionales
    0.40
     produkter
    0.38
     académicos
    0.37
    lerle
    0.36
    更多的
    0.36
    类似的
    0.36
    যানী
    0.36
    చేసిన
    0.36
    POSITIVE LOGITS
     dominating
    0.46
    ).
    0.46
    ¹.
    0.43
     façon
    0.40
     身
    0.39
     jellem
    0.38
    .¹
    0.38
     खासियत
    0.38
     측정
    0.38
    
    0.37
    Activations Density 0.038%

    No Known Activations