© 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. 4345
    Prev
    Next
    INDEX
    Explanations

    projections based on

    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
    했고
    0.49
    のではなく
    0.49
    :
    0.46
    ですし
    0.44
    었고
    0.43
    ;
    0.41
    ?;
    0.41
    ,
    0.39
    0.38
     หรือ
    0.37
    POSITIVE LOGITS
     ஆகியவை
    0.63
     ஆகிய
    0.57
     എന്നിവ
    0.55
     ஆகியவற்ற
    0.54
     всех
    0.51
     tất
    0.49
     všech
    0.49
     wobei
    0.49
     ყველა
    0.49
    等等
    0.48
    Activations Density 0.473%

    No Known Activations