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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4516
    Prev
    Next
    INDEX
    Explanations

    color assignment

    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
    trashItem
    0.46
     সরাস
    0.45
    㕮
    0.44
    TakePhoto
    0.42
     previewBuilder
    0.42
     excuses
    0.41
    
    0.41
    יא
    0.41
    噘
    0.41
    าราง
    0.40
    POSITIVE LOGITS
     நிற
    0.42
     red
    0.41
    violet
    0.38
     blue
    0.37
     hyperlinks
    0.37
    pink
    0.37
    紅色
    0.37
     merah
    0.36
     greenish
    0.36
     pink
    0.36
    Activations Density 0.002%

    No Known Activations