© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1013
    Prev
    Next
    INDEX
    Explanations

    install and add

    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_16k_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
    要知道
    1.76
    ه
    1.62
    <bos>
    1.58
     IEnumerable
    1.52
    چہ
    1.50
    ساز
    1.48
    ی
    1.45
    pthread
    1.40
    windigkeit
    1.40
     vogliono
    1.39
    POSITIVE LOGITS
    able
    1.83
    ership
    1.46
    BTW
    1.44
    𝚟
    1.40
    icted
    1.33
     ලද
    1.33
     তবে
    1.32
    tion
    1.30
     हुए
    1.25
     στον
    1.23
    Activations Density 0.198%

    No Known Activations