© 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. 10752
    Prev
    Next
    INDEX
    Explanations

    follow rules

    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
     genocide
    2.04
    𝑦
    1.99
    𝑟
    1.96
    𝑌
    1.95
    𝖑
    1.94
     velvety
    1.94
    𝐲
    1.88
     relegated
    1.86
     evoking
    1.86
     vertigo
    1.84
    POSITIVE LOGITS
    о
    1.96
    o
    1.67
    oğlu
    1.58
    tanggal
    1.58
     sido
    1.56
    께
    1.55
    ई
    1.54
    dr
    1.52
    με
    1.48
    tanto
    1.48
    Activations Density 0.000%

    No Known Activations