© 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. 11846
    Prev
    Next
    INDEX
    Explanations

    more + positive improvement

    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
    ş
    1.64
    ها
    1.51
    त
    1.50
    луйста
    1.45
    fler
    1.45
     ramifications
    1.39
     inclin
    1.38
    il
    1.36
    ຯ
    1.36
     kommt
    1.35
    POSITIVE LOGITS
     pełni
    1.54
     인해
    1.42
    tbody
    1.39
    snapshot
    1.36
    ternut
    1.36
    Snapped
    1.36
     truly
    1.35
    य
    1.35
    sst
    1.34
    siswa
    1.34
    Activations Density 0.095%

    No Known Activations