© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7649
    Prev
    Next
    INDEX
    Explanations

    exploring themes

    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_22_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
    으로
    1.60
    𝐭
    1.60
    ても
    1.60
    ර්
    1.56
    可以
    1.55
    可以将
    1.55
    𝐡
    1.53
    ually
    1.45
    𝐨
    1.41
     carboxylic
    1.41
    POSITIVE LOGITS
    i
    1.83
    ية
    1.65
    ی
    1.46
    ла
    1.43
    на
    1.42
     uncharted
    1.42
     possibilités
    1.37
    in
    1.36
    يئة
    1.31
     вариантов
    1.30
    Activations Density 0.069%

    No Known Activations