© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 144044
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific entities

    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
    涉
    0.46
     presentes
    0.45
    ل
    0.44
    на
    0.42
     السيا
    0.42
     hiện
    0.41
    至今
    0.41
    л
    0.41
     (\
    0.41
     melibatkan
    0.41
    POSITIVE LOGITS
    basically
    0.50
     ordnance
    0.46
    entretien
    0.45
    EU
    0.45
     hawks
    0.45
     শত্রু
    0.44
     বলিয়াই
    0.44
    Brussels
    0.44
    Engineer
    0.43
     bottomLeft
    0.42
    Activations Density 0.001%

    No Known Activations