© 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. 30450
    Prev
    Next
    INDEX
    Explanations

    no stars in photos

    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
     Matthews
    0.41
    Ми
    0.39
     experimental
    0.38
     Бе
    0.38
     MAT
    0.38
    笆
    0.38
    Если
    0.38
     elaboración
    0.38
    颜
    0.38
     contributions
    0.37
    POSITIVE LOGITS
    nove
    0.42
    堰
    0.39
     dissati
    0.38
     motorway
    0.37
     والذي
    0.37
    purecounter
    0.36
    بوط
    0.36
    รรค
    0.36
     ingot
    0.36
    umphed
    0.36
    Activations Density 0.001%

    No Known Activations