© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    good

    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
    ️
    2.32
    𝐬
    2.16
    𝐧
    2.15
    𝐩
    2.13
    ศาสตร์
    2.06
    ‍♀️
    2.06
    𝐦
    2.05
    ⁺
    2.01
    ⣶
    1.93
    绅
    1.93
    POSITIVE LOGITS
    en
    2.87
    ie
    2.58
    м
    2.53
    ル
    2.47
    д
    2.28
    ا
    2.21
    م
    2.18
    न्नाथ
    2.13
    撾
    2.12
    مون
    2.08
    Activations Density 0.068%

    No Known Activations