© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5570
    Prev
    Next
    INDEX
    Explanations

    lists items instructions

    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_65k_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
    Ձ
    0.44
     serialization
    0.44
     scintill
    0.44
    offline
    0.42
    中
    0.42
    ೊ
    0.42
     каттоо
    0.42
    Kali
    0.42
    ото
    0.41
    분
    0.41
    POSITIVE LOGITS
     طرق
    0.54
    inture
    0.45
     AAA
    0.44
     स्मार्ट
    0.43
     многое
    0.43
     طريقة
    0.43
     Adel
    0.43
     Beatles
    0.43
     своими
    0.43
     Greenville
    0.43
    Activations Density 0.220%

    No Known Activations