© 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-262K
    7. 19404
    Prev
    Next
    INDEX
    Explanations

    UK international affairs

    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
     rainwater
    0.44
    chloric
    0.39
     집중
    0.39
     deliberation
    0.38
    ճ
    0.38
    飽
    0.38
    二级
    0.37
    ပ်
    0.37
    StackTrace
    0.36
     мэ
    0.36
    POSITIVE LOGITS
     negotiating
    0.55
     Brexit
    0.52
     negotiate
    0.49
     negoti
    0.48
     post
    0.47
    Brexit
    0.46
     ইউরোপ
    0.45
     negotiable
    0.44
     Brits
    0.43
     EU
    0.42
    Activations Density 0.011%

    No Known Activations