© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8342
    Prev
    Next
    INDEX
    Explanations

    fit together, to save, Model, wagen, foliage

    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
    oding
    0.42
     Swift
    0.39
    wiring
    0.38
     swirl
    0.38
    knit
    0.38
    觞
    0.38
     wiring
    0.38
     dancer
    0.37
     sw
    0.36
    私が
    0.36
    POSITIVE LOGITS
    ‪‬
    0.52
     pensando
    0.51
    ⒏
    0.49
     הק
    0.48
     হইয়৷
    0.48
     SUVs
    0.46
     الك
    0.46
    បី
    0.46
    في
    0.46
    ugia
    0.45
    Activations Density 0.061%

    No Known Activations