© 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. 18869
    Prev
    Next
    INDEX
    Explanations

    performs much better

    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
     für
    0.50
    เพื่อ
    0.50
     یک
    0.48
     для
    0.47
    帮
    0.47
     redis
    0.47
    性别
    0.46
    สำหรับ
    0.45
    另一个
    0.45
     (
    0.44
    POSITIVE LOGITS
     forêts
    0.48
    보다는
    0.45
     atthakath
    0.44
     ماشینونه
    0.43
     densément
    0.42
     energi
    0.42
     hormati
    0.42
     energije
    0.41
    <unused21>
    0.41
     ماين
    0.41
    Activations Density 0.002%

    No Known Activations