© 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. 16-GEMMASCOPE-2-RES-262K
    7. 32695
    Prev
    Next
    INDEX
    Explanations

    IME followed by various concepts

    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_16_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
    Ду
    0.50
    สัก
    0.48
    主
    0.48
    くだ
    0.46
     productor
    0.45
     нужна
    0.45
     pretends
    0.43
     extensible
    0.43
     чор
    0.43
     conferences
    0.43
    POSITIVE LOGITS
    arez
    0.45
     على
    0.44
     gelişmeler
    0.43
     Cabo
    0.43
    垦
    0.42
    প্রিল
    0.42
     geli
    0.41
    ро
    0.41
     Honestly
    0.41
     אני
    0.41
    Activations Density 0.000%

    No Known Activations