© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37531
    Prev
    Next
    INDEX
    Explanations

    alone, therefore, all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ഒന്ന്
    0.54
    と呼ばれる
    0.48
     Waalaikumsalam
    0.48
     marais
    0.46
     العلماء
    0.46
     revolutionaries
    0.46
     ૩
    0.46
    راز
    0.45
    潮流
    0.45
    графія
    0.45
    POSITIVE LOGITS
    ing
    0.48
    ку
    0.48
    ist
    0.47
    ️
    0.45
    ery
    0.45
    ,
    0.45
    able
    0.43
     l
    0.43
    ке
    0.42
    er
    0.42
    Activations Density 0.005%

    No Known Activations