© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8563
    Prev
    Next
    INDEX
    Explanations

    connecting clauses and ideas

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adlı
    0.46
    하여
    0.44
    ﷻ
    0.40
     وذلك
    0.39
    тельской
    0.38
    🍽
    0.38
    माँ
    0.38
     diner
    0.37
    🏟
    0.37
    ޙ
    0.37
    POSITIVE LOGITS
     oops
    0.65
     Oops
    0.55
     여기가
    0.53
     этому
    0.52
     얘는
    0.46
     பளி
    0.46
    notice
    0.46
     اینجا
    0.45
     remember
    0.45
    注意
    0.44
    Activations Density 0.009%

    No Known Activations