© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9494
    Prev
    Next
    INDEX
    Explanations

    Australian government and legislation

    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_40_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
     Otago
    0.49
     Maori
    0.47
     ANZ
    0.47
     Māori
    0.44
    唷
    0.43
     ditem
    0.42
     wm
    0.42
    照明
    0.41
     Oceania
    0.41
    軐
    0.41
    POSITIVE LOGITS
     minister
    0.55
     Labor
    0.54
    Prime
    0.53
    Labor
    0.52
     federal
    0.52
     Prime
    0.49
    Minister
    0.48
     Minister
    0.48
    federal
    0.47
    minister
    0.46
    Activations Density 0.033%

    No Known Activations