© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69217
    Prev
    Next
    INDEX
    Explanations

    rate increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    execute
    1.37
    Vs
    1.24
     only
    1.22
     اك
    1.22
     گزار
    1.16
     자신이
    1.12
    ゴン
    1.11
    厌
    1.09
    only
    1.07
     obeying
    1.06
    POSITIVE LOGITS
    弹出
    1.54
    ussi
    1.52
    ://${
    1.46
    ضان
    1.46
    croft
    1.43
    っこ
    1.42
    وك
    1.42
    噺
    1.41
    яза
    1.40
    ieniu
    1.39
    Activations Density 0.000%

    No Known Activations