© 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. 11806
    Prev
    Next
    INDEX
    Explanations

    US states and Paraná

    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
    多い
    2.64
    Password
    2.64
     липня
    2.53
    ান
    2.53
    า
    2.52
    relatively
    2.50
    𝐧
    2.49
    ్యా
    2.46
    ighet
    2.45
     முருகன்
    2.45
    POSITIVE LOGITS
     شمالی
    2.91
    വസ
    2.76
    flake
    2.76
    tudo
    2.62
    ற்புத
    2.61
    ف
    2.59
    लम
    2.58
     predictably
    2.57
     grasslands
    2.57
    一个
    2.57
    Activations Density 0.039%

    No Known Activations