© 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. 8811
    Prev
    Next
    INDEX
    Explanations

    APA citation style

    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
     hiyo
    2.37
    いる
    2.34
    是通过
    2.29
     occhi
    2.25
    गौरतलब
    2.23
    是谁
    2.20
     Σε
    2.19
    ∑</
    2.17
     közül
    2.16
    માં
    2.13
    POSITIVE LOGITS
    তে
    2.56
    𝚌
    2.56
     eigenvector
    2.43
    𝚛
    2.38
    IgnoreCase
    2.37
    𝗙
    2.30
    𝚕
    2.29
    𝚗
    2.25
    𝗰
    2.17
    𝗸
    2.17
    Activations Density 0.003%

    No Known Activations