© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11543
    Prev
    Next
    INDEX
    Explanations

    australia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ality
    1.71
    etr
    1.59
    etric
    1.59
    ছেন
    1.54
    ో
    1.53
    ोम
    1.51
    聩
    1.50
    薬
    1.48
    ረጥ
    1.44
    imiya
    1.44
    POSITIVE LOGITS
     australia
    2.56
    Australia
    2.52
     Australia
    2.47
     AUSTRAL
    2.40
     Canberra
    2.15
    澳洲
    2.13
     Queensland
    2.12
     Australian
    2.12
     Melbourne
    2.05
     Tasmania
    2.02
    Activations Density 0.107%

    No Known Activations