© 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. 18960
    Prev
    Next
    INDEX
    Explanations

    redundant or contrasting 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_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
     Magazine
    0.46
    Currently
    0.43
     mujeres
    0.42
    \
    0.42
    かしい
    0.41
     Ba
    0.40
     dre
    0.40
    hola
    0.40
    č
    0.39
     Roberto
    0.39
    POSITIVE LOGITS
    สำหรับการ
    0.50
    សម្រាប់ការ
    0.50
     nerfs
    0.48
    য়োজনীয়
    0.46
    चर्स
    0.43
     desks
    0.43
    
    0.43
     guarant
    0.42
     liability
    0.42
    ไฮ
    0.41
    Activations Density 0.001%

    No Known Activations